Keywords: Biometric Systems and Bioinformatics, Systems Safety and Security, Human-Computer Interaction
Abstract: Authorship recognition from micro-blogs such as Twitter is a challenging task due to limitation of text length to 140 characters. However, identification of micro-blog authors is crucial in many cyber-crime investigations as well as in forensic applications. So far, traditional linguistic profiles such as Bag-Of-Words (BOW) and style-based markers have been investigated for identification of micro-blog authorship. The social interactive data in micro-blogs remained understudied for this purpose. In this paper, we examined authorship recognition based on the social interactions of users in Twitter and present a comparative analysis with BOW and style-based features. We obtained 97% recognition rate on a database of 70 Twitter users, which validates the superiority of using social interactive data compared to traditional linguistic profiles.

Keywords: Machine Learning, Optimization, Evolutionary Computation
Abstract: Casting machine learning as a type of search, we demonstrate that the proportion of problems that are favorable for a fixed algorithm is strictly bounded, such that no single algorithm can perform well over a large fraction of them. If an algorithm greatly excels on a class of problems (e.g., convex problems), that class must necessarily be small. We give an upper bound on the expected performance for a search algorithm as a function of the mutual information between the target and the information resource (e.g., training dataset), proving the importance of certain types of dependence for machine learning. Lastly, given that the expected per-query probability of success for an algorithm is mathematically equivalent to a single-query probability of success under a distribution (called a search strategy), we prove that the proportion of favorable strategies is also strictly bounded. Thus, whether one holds fixed the search algorithm and considers all possible problems or one fixes the search problem and looks at all possible search strategies, favorable matches are exceedingly rare. The forte (strength) of any algorithm is quantifiably restricted.

Keywords: Neural Networks and their Applications, Swarm Intelligence, Hybrid models of NN
Abstract: In recent years, several new methods for missing data estimation have been developed. Real world datasets possess the properties of big data being volume, velocity and variety. With an increase in volume which includes sample size and dimensionality, existing imputation methods have become less effective and accurate. Much attention has been given to narrow Artificial Intelligence frameworks courtesy of their efficiency in low dimensional settings. However, with an increase in dimensionality, these methods yield unrepresentative imputations with an impact on decision making processes. Therefore in this paper, we present a new framework for missing data imputation in high dimensional datasets. A Deep Learning technique is used in conjunction with a swarm intelligence algorithm. The performance of the proposed technique was experimentally tested and compared against other existing methods on an off-line dataset. The results obtained have shown promising potential with slightly longer execution times, which are a worthy trade-off when accuracy is of importance.

Keywords: Fault Monitoring and Diagnosis, Quality/Reliability Engineering
Abstract: Software often requires frequent updates to improve performance and reliability. Typically, a general update process is performed after terminating a program although this is not applicable to applications that require non-disruptive services such as networks and satellites. In order to address this issue, network service providers often provide a technology termed as an in-service software upgrade (ISSU) that performs continual updates without stopping the services. However, it requires additional devices or facilities, and the system structure in this case becomes complicated and additional economic costs are incurred. In this study, the design and implementation of a functional-level hot-patching platform are presented for executable and linkable format (ELF) binary program, based on an ARM and an Intel processor to add or update functions necessary to provide non-stop services. The proposed platform was validated on devices by using both Raspberry Pi and a general x86_64 personal computer. Experiments with an iPerf3 server and a drone simulator on each device demonstrated the effectiveness of the proposed hot-patching platform in achieving non-disruptive services with a negligible latency of less than 10 ms.

Keywords: Robotic Systems, Intelligence Interaction, Human-Computer Interaction
Abstract: One of the major functions of intelligent robots such as social or home service robots is to interact with users in natural language. Moving on from simple conversation or retrieval of data stored in computer memory, we present a new Human-Robot Interaction (HRI) system which can understand and reason over environment around the user and provide information about it in a natural language. For its intelligent interaction, we integrated Dynamic Memory Networks (DMN), a deep learning network for Visual Question Answering (VQA). For its hardware, we built a robotic head platform with a tablet PC and a 3 DOF neck. Through an experiment where the user and the robot had question answering interaction in our customized environment and in real time, the feasibility our proposed system was validated, and the effectiveness of deep learning application in real world as well as a new insight on human robot interaction was demonstrated.

Keywords: Image Processing/Pattern Recognition, Machine Learning, Optimization
Abstract: Owing to its simplicity and efficacy, orthogonal matching pursuit (OMP) has been a popular sparse representation method for compressed sensing and pattern classification. As a recent extension of OMP, generalized OMP (GOMP) improves the efficiency of OMP by identifying multiple atoms each iteration. Nonetheless, GOMP utilizes the mean square error (MSE) criterion as the loss function, which has been proven to rely on the Gaussianity assumption of the noise distribution and sensitive to non-Gaussian noise. In this paper, we propose a robust sparse representation method, called information-theoretic generalized OMP (ITGOMP), to reduce the limitation of GOMP. The key idea is to minimize the correntropy based information-theoretic loss function, which is independent of the noise distribution. We also devise a half-quadratic based algorithm to tackle the optimization problem. Finally, an ITGOMP based classifier is developed for robust pattern classification. The experiments on public realworld databases verify the effectiveness and robustness of the proposed method for classification.

Keywords: Optimization, Machine Learning, Computational Intelligence
Abstract: Bayesian Optimization or Efficient Global Optimization (EGO) is a global search strategy that is designed for expensive black-box functions. In this algorithm, a statistical model (usually the Gaussian process model) is constructed on some initial data samples. The global optimum is approached by iteratively maximizing a so-called acquisition function, that balances the exploration and exploitation effect of the search. The performance of such an algorithm is largely affected by the choice of the acquisition function. Inspired by the usage of higher moments from the Gaussian process model, it is proposed to construct a novel acquisition function based on the moment-generating function (MGF) of the improvement, which is the stochastic gain over the current best fitness value by sampling at an unknown point. This MGF-based acquisition function takes all the higher moments into account and introduces an additional real-valued parameter to control the trade-off between exploration and exploitation. The motivation, rationale and closed-form expression of the proposed function are discussed in detail. In addition, we also illustrate its advantage over other acquisition functions, especially the so-called generalized expected improvement.

Keywords: Robotic Systems, Cooperative Systems and Control, Human-Machine Cooperation & Systems
Abstract: In interactive human-robot path-planning, a capability for expressing the path topology provides a natural mechanism for describing task requirements. We propose a topology-aware RRT* algorithm that can explore in parallel any given set of topologies. The topological information used by the algorithm can either be assigned by the human prior to the planning or be selected from the human in posterior path selection. Theoretical analyses and experimental results are given to show that the optimal path of any topology can be found, including a winding topological constraint wherein the robot must circle one or more objects of interest.

Keywords: Machine Learning, Decision Support Systems
Abstract: Accurate localization of brain regions responsible for language and cognitive functions in Epilepsy patients should be carefully determined prior to surgery. Electrocorticography (ECoG)-based Real Time Functional Mapping (RTFM) has been shown to be a safer alternative to the electrical cortical stimulation mapping (ESM), which is currently the clinical/gold standard. Conventional methods for analyzing RTFM signals are based on statistical comparison of signal power at certain frequency bands. Compared to gold standard (ESM), they have limited accuracies when assessing channel responses.

In this study, we address the accuracy limitation of the current RTFM signal estimation methods by analyzing the full frequency spectrum of the signal and replacing signal power estimation methods with machine learning algorithms, specifically random forest (RF), as a proof of concept. We train RF with power spectral density of the time-series RTFM signal in supervised learning framework where ground truth labels are obtained from the ESM. Results obtained from RTFM of six adult patients in a strictly controlled experimental setup reveal the state of the art detection accuracy of ~ 78% for the language comprehension task, an improvement of 23% over the conventional RTFM estimation method. To the best of our knowledge, this is the first study exploring the use of machine learning approaches for determining RTFM signal characteristics, and using the whole-frequency band for better region localization. Our results demonstrate the feasibility of machine learning based RTFM signal analysis method over the full spectrum to be a clinical routine in the near future.

Keywords: Assistive Technology
Abstract: Many wearable robots are not fully capable of fitting the motion of the wearer, owing to their limited degrees of freedom(DOF). This limitation disturbs motions such as corner curving, which are required in daily life. In this study, the effect of the DOF restriction on the corner curving motion was observed and analyzed. The gait motions, when curving a round corner with and without the restriction of out-of-sagittal plane motion, were compared using a wearable device which could restrict hip adduction/abduction and rotation. The result suggested that the restriction not only decreased the range of motion of hip adduction/abduction and rotation, but also changed the center of mass (COM) trajectory. Owing to the disturbance applied during the stepping motion of the outer leg, the COM trajectory moved further from the corner in the trials with restriction. Thus, the distance between COM and the base of support of the inner foot became larger during the swing phase of the outer leg, which possibly increased the risk of loss of balance. Furthermore, it was also suggested that an assistive torque, which does not consider curving motion, possibly increases such risk.

Keywords: Image Processing/Pattern Recognition, Computational Intelligence, Cybernetics for Informatics
Abstract: The scale of the modern city has been expanding, which leads to a lot of serious environmental pollution problems. Among them, the air pollution problem is the most prominent. In order to control the air pollution in urban cities, the government has deployed a lot of air pollutant monitoring equipment which produce massive multi-dimensional time series data. Through the motif discovery and analysis of these multi-dimensional time series, we can find the relationships and the rules between air pollutants to provide support and suggestions for controlling the air pollution. In this paper, a novel method on motif discovery and analysis for large-scale multi-dimensional time series data is proposed. The new method can effectively find multi-dimensional motifs and the correlation between them as much as possible, which reveals the underlying rule of different air pollutants. It is validated on practical historical data of air pollutants in Beijing. The experimental results show that the proposed method could obtain better performance than the related work.

Keywords: Optimization, Media Computing, Machine Vision
Abstract: The traditional affine iterative closest point (ICP) algorithm is fast and accurate for affine registration between two point sets, but it is easy to fall into local minimum. This paper proposes a robust Affine ICP algorithm based on corner points. First, an objective function is established under the guidance of corner points, where the corner points as the shape control point guides the affine registration of 2D point sets. Then, at each step of the algorithm, the affine transformation obtained by the last iterative step is used to establish the correspondence of these two point sets. Next, the new affine transformation is solved by using the objective function under the guidance of the corner points. Experimental results demonstrate that the robustness and convergence of our algorithm are greatly improved compared with the traditional affine registration algorithm.

Keywords: Heuristic Algorithms, Optimization, Manufacturing Systems/Automation
Abstract: This paper address the problem of scheduling a set of jobs with non-zero ready times and incompatible job families on a set of identical parallel batch machines so as to minimize the total weighted tardiness. In this problem, each machine can process several jobs of a same family simultaneously as a batch as long as the machine capacity is not exceeded. Jobs of a family has the same processing time and the batch ready time is equal to the largest ready time among all the jobs in the batch. To solve the problem, we propose two meta-heuristic algorithms based on Iterated Greedy (IG) and Simulated Annealing (SA), respectively. The performance of our algorithms is evaluated and compared by computational experiments on a large benchmark of instances from the literature. The obtained results indicate that the proposed algorithms has good performance compared to two meta-heuristic algorithms proposed for the same problem.

Keywords: Machine Vision, Multimedia Systems, Image Processing/Pattern Recognition
Abstract: This study proposes a system-on-a-chip, fieldprogrammable gate array (FPGA)-based real-time video processing platform for human action recognition. We provide the details of a hardware implementation for real-time human activity recognition in 3D scenes, including capture, processing, and display. The proposed platform is implemented by adding a two-stage preprocessing step to improve the results of a saliency map and utilizing the inherent parallelism of FPGAs. Appropriate circuits for parallelized operation of Harris and Hessian interest point detection and support vector machine classifiers are discussed.

Keywords: Evolutionary Computation, Heuristic Algorithms, Computational Intelligence
Abstract: It is difficult to find optimum solutions by using evolutionary algorithms (EAs) in high-dimensional search space as compared with low-dimensional search space. For solving such a high-dimensional problem, we propose a search space reduction approach in EAs. For reducing the search space, the approach repeats fixing the value of one design variable which should be reduced from the search space. We apply this approach to optimize the high-dimensional portfolio replication problem. In the numerical experiments, we show that our search space reduction approach in EAs finds good solutions in the reduced search space as compared with a traditional approach which searches solutions in the whole solution space.

Keywords: Biometric Systems and Bioinformatics, Image Processing/Pattern Recognition
Abstract: 3D face recognition is a popular research area due to its vast application in biometrics and security. Local featurebased methods gain importance in the recent years due to their robustness under degradation conditions. In this paper, a novel high-order local pattern descriptor in combination with sparse representation based classifier (SRC) is proposed for expression robust 3D face recognition. 3D point clouds are converted to depth maps after preprocessing. Multi-directional derivatives are applied in spatial space to encode the depth maps based on the local derivative pattern (LDP) scheme. Directional pattern features are calculated according to local derivative variations. Since LDP computes spatial relationship of neighbors in a local region, it extracts distinct information from the depth map. Multiscale depth-LDP is presented as a novel descriptor for 3D face recognition. The descriptor is employed along with the SRC to increase the range data distinctiveness. A histogram on the derivative pattern creates a spatial feature descriptor that represents the distinctive micro-patterns from 3D data. We evaluate the proposed algorithm on two famous 3D face databases, FRGC v2.0 and Bosphorus. The experimental results demonstrate that the proposed approach achieves acceptable performance under facial expression.

Keywords: Cybernetics for Informatics, Image Processing/Pattern Recognition
Abstract: The high-level feature representation of deep convolutional neural networks (ConvNets) has proven to be superior to hand-crafted low-level features. Thus, this study investigates the effect of fusing such high-level features from multi-deep ConvNets under an application of visual object/scene categorization. In which, three pre-trained ConvNets are exploited as feature extractors, a single hidden layer is adopted to transform the high-level representations to a low dimensional feature space and that are fused to harness the rich cues of the individual features.

The experimental outcomes on six benchmark databases demonstrate that regardless of variation in visual statistics and tasks the fusion of multi-ConvNets' high-level features can meliorate the classification accuracy compared with a single modality, different ConvNets contain complementary cues of visual contents, and the fusion is capable of producing a very competitive performance to the state-of-the-art methods. Besides that, this fusion approach can be an effective complement to the ConvNets.

Keywords: Computational Intelligence, Machine Learning
Abstract: This paper proposes an improved KNN algorithm to overcome the class overlapping problem when the class distribution is skewed. Different from the conventional KNN algorithm, it not only finds out the k nearest neighbors of each sample (even the test object itself) in the training dataset, but also the neighbors of the unknown test object. Then the validity value of a data point is computed based on the label of the data and the labels of its k nearest neighbors. A classifier is designed to assign the unknown test object to a class membership based on the proposed validity ratings equations. A numerical analysis provides a detailed example to demonstrate the effectiveness of the algorithm. The improved KNN algorithm is compared with the conventional KNN and the modified KNN algorithm on the real world wine data with the increasing number of k from 1 to 20. The experimental results show that the proposed improved KNN algorithm outperforms the conventional KNN and the modified KNN algorithm. In addition, classification accuracy of KNN algorithm and our algorithm in terms of various combinations of k-value and k-fold cross validation are compared. It is found that while the classification accuracy of the conventional KNN algorithm has changed drastically, our algorithm remains constantly high over the k values. Additionally, the conventional KNN algorithm has shown a declining trend when k is large, i.e. k = 20, while our algorithm remains stable.

Keywords: Mechatronics, Medical Informatics
Abstract: In this work, a wearable instrumented smart clothes with an accelerometer sensor embedded on the upper abdomen close to the diaphragm was used to detect respiration of subjects. A detection algorithm was proposed and verified with 30 testing cases on male and female subjects separately. More than 97% of accuracy is achieved by comparing with the detection results from respiratory belt conducted simultaneously. This clothes and respiratory detection is extremely useful to monitor human’s respiration when the subjects are in sleep and hence could be used for the detection of sleep apnea syndrome.

Keywords: Wearable Computing
Abstract: While the ability to perceive attitude in 3D trajectory of the movement is a basic concept of a motion capture, a 9-axis inertial measurement unit (IMU) device containing accelerometer, gyroscope and magnetometer is introduced as a challenge for motion tracking device. In this paper, a modular architecture in terms of accuracy on orientation of the sensor output, implemented for wearable motion capture system in attitude estimation. It contains 13 IMU module devices as a sensory network attached in the human body for reconstructing human attitude estimation. The system is integrated as quaternion-based implementation where several methods are separately used for achieving better result. The first proposed methods are using digital motion processor for gaining accurate data and directly calculated inside the sensor itself. Secondly, a complementary filter (CF), fused using gradient descent algorithm. Another approach method is combining CF with Mahony filter. Furthermore, all of approaches are working with DMP system to minimize the accumulative errors. As a validation, a passive manipulator robot containing encoders is used for comparison. The experimental results showed that all of the proposed methods can work properly and they represented acceptable performances and achieve accuracy for orientation.

Keywords: Evolutionary Computation
Abstract: In recent years, semantics-based crossover operators have attracted attention for efficient search in Genetic Programming (GP). Geometric Semantic Genetic Programming (GSGP) is one of the methods, in which a convex combination of two parents is used for creating an offspring. We have previously proposed an improved GSGP, Deterministic GSGP. In Deterministic GSGP, the convex combination is relaxed to an affine combination, and the optimum ratio for the affine combination is determined so that an offspring can always have better fitness than its parents. However, Deterministic GSGP has a problem that search might fall into local optima due to premature convergence. In this paper, we propose a new generation alternation model for maintaining population diversity. In the proposed model, all the individuals have opportunities to generate offspring as parents. We compared our proposed model with the conventional Deterministic GSGP in search performance, and showed its effectiveness.

Keywords: Assistive Technology
Abstract: This paper presents new approach for unobtrusive indoor fall detection by an IR thermal array sensor. Unlike existing methods that run fall detection at server and require high communication and processing rates, we perform fall detection within the sensor node by a computationally inexpensive algorithm that signals the server only when a fall occurs. Experiments with prototype design show that such formulation provides robust and real-time fall detection even in a noisy environment.

Keywords: Human Factors, Human-Computer Interaction, Systems Safety and Security
Abstract: We report an experimental study that involves understanding how display (conventional or ecological) and system mode (profiting, neutral or losing) affect financial trading performance and risk preference. Twenty-four undergraduate and graduate student participants interacted with a financial trading simulator in the playback of a real market. Each participant completed a conventional display scenario and an ecological display scenario that were presented in a counterbalanced sequence. The participants performed buying and selling executions on a financial product based on the portfolio status and their own judgement of the market movement. The participants’ trading behaviors were recorded. The conventional display included a market panel, a portfolio panel, a trading history panel and a trading command panel. The ecological display included all panels from the conventional display as well as a multivariable visualization showing the causal relationship between the market, the portfolio and the trading executions. Results on the display type effect showed that the ecological display neither improved nor degraded trading performance. However, the participants held a significantly larger position size with the ecological display than with the conventional display, indicating a risk-seeking portfolio with the ecological display. Results on the system mode effect showed that the participants were more likely to take a moderate risk-seeking action (i.e., holding the portfolio) while the system was making a profit than while the system was in a neutral state. This study is the first experimental study to evaluate ecological displays in a financial trading setting, and has implications for designing financial trading displays.

Keywords: Brain-based Information Communications, Human Factors, Human Performance Modeling
Abstract: In this study, we investigate whether sparse coding helps explain the semantic representation in human cerebral cortex. We show this by using sparse coding to model semantic representation in the cerebral cortex. We propose three methods for estimating semantic representation from brain activity data. For estimating a new semantic representation, in the first method, we use only a semantic representation dictionary obtained via sparse coding. The semantic representation estimated using this method is more similar to the actual semantic representation of the cerebral cortex than that estimated without sparse coding. In the second method, we use only a brain activity dictionary obtained via sparse coding. The semantic representation estimated using this method is also better than that estimated without sparse coding. In addition, in the third method, we estimate semantic representation by applying sparse coding to both semantic representation and brain activity data. The semantic representation estimated by using this third method is better than that estimated by the first or second methods. Through the above three experiments, we have confirmed that sparse coding helps explain the semantic representation in human cerebral cortex.

Keywords: Human-Machine Cooperation & Systems, Communications, Robotic Systems
Abstract: In human face-to-face communication, embodied sharing using the synchrony of embodied rhythms is promoted by embodied interactions. Therefore, embodied interactions are important for smoothly initiating coexistence and communication. When there is embodied interactions with direct contact, it plays to synchronize embodied rhythms effectively. Hug behavior is one of the types of embodied interactions that involve direct contact. In this type interactions, humans whole-body contact with each other. In the case of interaction between a human and a robot, robot synchronizes embodied rhythms effectively using hug behaviors. Furthermore, embodied interactions are expected to be promoted by hug behaviors, in which robot actively approaches and requests to the human. Therefore, in this paper, we develop a hug request motion model of robot during active approach to human. At first, mutual hug behaviors between humans are analyzed in an environment with a voice greeting. Then, on the basis of this analysis results, a hug request motion model during active approach to human is developed. This model generates a hug behavior in which a robot active approaches and requests a hug behavior to a human. In addition, we developed a hug robot system that uses the developed hug request motion model. Using this robot system, the effectiveness of the proposed model is demonstrated by a sensory evaluation.

Keywords: Medical Informatics, Neural Networks and their Applications, Image Processing/Pattern Recognition
Abstract: Diabetic Foot Ulcers (DFU) is a major complication of Diabetes, which if not managed properly can lead to amputation. DFU can appear anywhere on the foot and can vary in size, color, and contrast depending on various pathologies. Current clinical approaches to DFU treatment rely on patients and clinician vigilance, which has significant limitations such as the high cost involved in the diagnosis, treatment and lengthy care of the DFU. We introduce a dataset of foot images, which contain 705 foot images. We provide the ground truth of ulcer region and the surrounding skin that is an important hint for clinicians to assess the progress of ulcer. Then, we propose a two-tier transfer learning from bigger datasets to train the Fully Convolutional Networks (FCNs) to automatically segment the ulcer and surrounding skin. Using 5-fold cross-validation, the proposed two-tier transfer learning FCN Models achieve a Dice Similarity Coefficient of 0.794 (±0.104) for ulcer region, 0.851 (±0.148) for surrounding skin region, and 0.899 (±0.072) for the combination of both regions. This demonstrates the potential of FCNs in DFU segmentation, which can be further improved with a larger dataset.

Keywords: Human-Computer Interaction, Human Factors, User Interface Design
Abstract: This paper presents results of a survey that explored the challenges low-income mobile users of Dhaka, Bangladesh (N = 131) face in mobile text entry. Results revealed that all users use the Bengali language at some capacity to compose text, yet many (are forced to) write with the Roman alphabet. Both feature phone and smartphone users feel that the existing text entry techniques are difficult to learn and use. The fact that some knowledge of the English language is necessary, even to use many popular Bengali text entry techniques, frustrates them as it compromises their entry speed and accuracy. Results also suggest that mobile phones and mobile text entry are more popular among younger and educated users. Further, smartphone users spend more time and engage in more text entry episodes than feature phone users.

Keywords: Multimedia Systems
Abstract: Large-field image stitching and 3D reconstruction are two hot topics in computer visions. Generally,only a small amount of overlapped area is required in large-field image stitching. On the other hand, cameras usually share almost the same field of view for multi-view 3D reconstruction,which guarantees enough overlapped areas to calculate 3D information of the target scene. To realize the two purposes using a single imaging device simultaneously, we propose a novel structure design of camera array, which combines multiple cameras with gradually-changed field of view. Based on the proposed camera array, we can firstly calculate the depth of points in 3D space, then a panoramic image with large field of view can be generated in consideration of the depth information. A prototype imaging system based on the novel camera-array structure is realized, and then real-scene imaging experiments are implemented to prove the feasibility and effectiveness of our method.

Keywords: Entertainment Engineering, Interactive and Digital Media, Fuzzy Systems and their applications
Abstract: Pervasive mobile games utilise contextual data about players and their environment to explore new means of interaction and enhance the gaming experience. However, the inherent imperfection of contextual data acquisition poses a challenge for developers and designers of pervasive games. In these games, both sensor inaccuracies and uncertainty need to be identified and properly handled to prevent disrupting the gaming experience. This paper presents a model for the development of pervasive mobile games based on fuzzy systems. It promotes the use of fuzzy set theory to represent context uncertainty and applies fuzzy logic to design game rules. A pervasive mobile game, called Radar, is presented to showcase the model's applicability; the game employs contextual data from GPS and sensors to infer the animation frequency of a simulated radar with a type-I Mamdani fuzzy inference system. Thus, the proposed model is capable of handling sensor inaccuracies while providing an intuitive approach to the design of pervasive games.

Keywords: Information Visualization
Abstract: One of the greatest challenges for computer science in education is the capacity to provide environments that are intelligent and adaptable to the real needs of students. In order to create efficient adaptive mechanisms for educational content, student models are proposed to identify and to predict the real knowledge level of students. Such models are useful not only for computer systems but also to assist students and instructors in the teaching-learning process so that such models may be visualized by them in a intuitive way. Thus, this study proposes the integration of information visualization tools aimed at creating an open student model that allows students and instructors to access the information inferred by the student model. For validation, the proposed model was implemented, integrated, and tested in a real ubiquitous learning environment. Results show users' satisfation when such feature is available, as well as their perception about different visualizations.

Keywords: Medical Informatics, Design Methods
Abstract: In recent years, many online health communities (OHCs) are established to provide the patients with the services of disease prevention and self-management. Patients in those online health communities discuss their health conditions and share their experiences with other patients using narrative texts in the posts. Those posts contain a vast amount of patients’ information, including drugs, symptoms, conditions, etc. They are really valuable for clinical research. However, it is hard for information systems to automatically extract the clinical knowledge from those posts to provide knowledge-based services to online patients. This paper investigates the characteristics of those post contents and accordingly proposes an encoding method with Systematized Nomenclature of Medicine -- Clinical Terms (SNOMED CT) to process the texts into encoded and structured contents to help the analytic system in the OHCs to discover the biomedical knowledge. Based on our experimental result, the proposed method can effectively extract the biomedical knowledge from the posts and enhance the ability of clinical knowledge discovery online to improve the patient support.

Keywords: Information Visualization, Enterprise Information Systems, Expert and Knowledge-based Systems
Abstract: The unstructured data, whose volume grows exponentially, often hide important and even vital information for society and companies. It takes a lot of work to extract information such as the nature of consumption in a category of individuals, trends etc. When it comes to statistical data, it is often very useful to synthesize this kind of information in the form of graphical representations. In this paper, we present an approach for processing unstructured data containing statistics in order to represent them graphically. An application that implements this process is also presented.

Keywords: Human Factors, Human-Computer Interaction, Systems Safety and Security
Abstract: Technology is in a constant state of evolution, which allows for new and cunning cyber-attacks and tactics. Out of all these tactics, the exploitation of human cognitive biases in response to phishing attacks is challenging to defend against. The purpose of this study was to determine if humans could discriminate fraudulent Uniform Resource Locators (URLs) or links from legitimate URLs without the aid of specific hardware or software. We also explored whether simple textual manipula- tions were easier to detect compared to complex manipulations. Participants (N = 1044) completed the following: (1) A demo- graphic questionnaire including their internet and email usage, (2) a role-playing exercise where participants were shown a series of emails from an inbox and had to select the action(s) that they would take, and (3) a series of questions related to technology and security to assess their prior knowledge and awareness of phishing. Results indicated that it was difficult for participants to correctly identify URLs when checking email. Results also revealed that difficulty in detecting simple textual manipulations versus complex manipulations was category dependent.

Keywords: Assistive Technology, Human-Computer Interaction, Machine Learning
Abstract: The field of Sign Language Recognition (SLR) has become an increasingly popular research topic. The goal of this study is an SLR system that will be capable of identifying a subset of 50 of the most common American Sign Language (ASL) word signs using surface electromyography and accelerometer data for multiple signers. All data was collected from deaf, fluent ASL users. A windowing approach is used with different time domain features for feature extraction. The samples are divided into one and two-handed signs, each of which are used to train a Support Vector Machine classifier. Samples from all but one subject are used to train the classifiers. The classifiers are then tested on both data held out from the subjects used for training and the subject that was left out. The resulting system had an average accuracy of 63.1% for trained subjects and 34.59% for the subject left out. To compare this approach to others, 40-word and 7-word sign sets are trained and tested using this method. The proposed system performed comparably with literature for the 40-word set, and better for the 7-word set.

Keywords: Human-Machine Cooperation & Systems, Augmented Cognition, Robotic Systems
Abstract: This paper studies human-swarm interaction performance by evaluating both the neurophysiological and behavioral characteristics of human subjects. By utilizing our unique test facility, we conduct a series of real-world-scenario-inspired tasks in which subjects are asked to guide a group of ground robots with various configurations to arrive at a sequence of randomly assigned targets. A range of neurophysiological and behavioral sensors are used to measure how cognitive states, e.g., cognitive load, behaviors, e.g., gazes, and performances, e.g., success rate, of human performs unfold in real time as the tasks evolve. Through an analysis of changes in gaze and cognitive load, we gain a wider understanding of the mechanisms of task failure; most notably the difficulty of estimating the complete state of the robotic group. The results of this study can help to inform the design of efficient interaction policies which can maximize task effectiveness between humans and robot swarms.

Keywords: Information Visualization, Image Processing/Pattern Recognition
Abstract: Research efforts have been devoted to extraction and visualization of vortices in an unsteady (turbulent) flow. Characterizing the behaviors of the flow, vortices are identifiable as regions using a vortex detector known as the lambda2-criterion. Isosurface visualization renders vortex regions based on a chosen isovalue. However, it is highly challenging to choose one isovalue suitable for visualizing vortex regions of the entire flow field. A solution is the approach of maxima score that localizes vortex regions identified by the lambda2-criterion based on similarity scores relative to local extrema. The approach is however sensitive to noise or floating-point errors in the flow, leading to clutter in vortex visualization. As a feasibility study, this paper presents an threshold estimation to overcome this sensitivity. The estimation involves clustering on local minimum differences in lambda2 scalar values derived from the gradient tensor of the velocity field, and yields multiple values of the threshold without user intervention. Tested on several flows in various size and Reynolds number, the results of the threshold estimation confirmed overcoming the sensitivity of the maxima score approach. This indicates a potential of the threshold estimation to improve the robustness of the approach for vortex extraction and visualization.

Keywords: Information Visualization
Abstract: Visualization of fluid flows at a high-Reynolds number (Re ~ 10^5) presents difficulties for user comprehension due to density and ambiguous interactions between vortices. Prior work has used cluster-based reduced-order modelling (CROM) to analyze the wake of a High-Speed Train (HST) with Re = 86000. In this paper, we present a novel surface visualization to convey the spatiotemporal changes undergone by clustered vortices in the HST wake. This visualization is accomplished through dimensional reduction of 3D volumetric vortices into 1D ridges, and physics-based feature tracking. The result is 3D surfaces visualizing the behavior of the vortices in the HST wake. Compared to conventional still-image representations, these surfaces allow the user to quickly compare and analyze the two shedding cycles identified via CROM. The spatiotemporal differences of the primary vortices in these shedding cycles provide analytic insight to influence the aerodynamics of the HST.

Keywords: Decision Support Systems, Smart Sensor Networks, Machine Learning
Abstract: As the emerging development of IoT circumstance,on-line detections or observations of a system states become easier by facilitating its corresponding multi-sensory responses,and thus the description of a system behavior becomes clearer. Abundant on-line multi-channel information from the embedded sensors would be advantageous to the understanding of the system. Though having the information, it is still uneasy to thoroughly assess the integrity behavior of the system without a eligible system identification method. In the study, through a recurrent function approximation by an integrated multi- regression of support vector regression (SVR), the identification has been developed and represented as a family of characteristic functions. With the set of characteristic functions, a design of IoT based live interaction of adaptive control or human-machine system could hereafter followed up. The study constructed primarily the SVR based framework of the recurrent multi- sensor system identification. There are two major contributions of the study: First, an IoT aspect for the discovery of the multiple regression extended from an underlying SVR, second, a technical overcoming in the realization of the recurrent framework of SVR.

Keywords: Medical Informatics
Abstract: Skiing is one of the most popular winter sports in the world. Even though the equipment has been improved for preventing injuries during skiing, injury risks of the lower extremity are still high. It is necessary to investigate injury risk by motion analysis during skiing. The wearable motion capture system consisting of inertial sensors and insole pressure sensors can be utilized due to restrictions of conventional optical motion capture system. In this study, the motions for short- and middle-turns during skiing were analyzed using a wearable motion capture system and the multi-scale computer simulation technology. Seven male certified ski coaches participated in this study and their full body motion and foot pressure data were simultaneously recorded by the wearable motion capture system. Joint kinematics and kinetics in the hip, knee and ankle of the right lower extremity were analyzed during short- and middle-turns. Even though a slight difference in the joint kinematics between two turns was predicted, the joint forces and moments for middle-turn were higher than those for short-turn. Because these higher joint forces and moments can result in osteoarthritis or ligament injury at the joint, injury risk of the joint for middle-turn may be higher than that for short-turn. This study confirms that the wearable motion capture system is useful for measuring the motion and plantar pressure data in outdoor sports such as skiing.

Keywords: Medical Informatics, Biometric Systems and Bioinformatics
Abstract: This paper discloses the development of a phase oscillator model for radiotherapy which predicts future position of the lung tumor based on the current and past phase of lung tumor, respiration waveform and heartbeat measurements. We assumed that these phases can be measured at the same time, and tried the prediction of 0.15s ahead of time position of the superior-inferior direction of a lung tumor motion. The result of offline simulation shows that the proposed model provides the estimated position of the tumor with 1.5mm RMS error.

Keywords: Medical Informatics, Human Performance Modeling, Information Visualization
Abstract: Kinetic and spatiotemporal gait analysis provides important information for the treatment and rehabilitation of patients with gait disorders. Although motion analysis laboratories with infrared motion capture cameras and force plates are the gold standard measurement technologies for analysis, they are, in most cases, impractical for community health centers or general clinical settings because of their cost, scale, and usability. This paper presents an accessible gait analysis system that uses simultaneous measurements of instrumented insoles and a laser range sensor (LRS). In the proposed system, GRF and COP are estimated by sensor analysis taken from the insoles. Strides step width, cadence, and walking speed are measured by the LRS. In addition, stance durations including single limb support and double stance are detected at the insoles from accurate measurements of initial and end foot contact time. The GRF estimation method derived from the insole sensors and the integrated system with the LRS have been validated by measuring straight walking and comparing results with data obtained from motion analysis laboratories.

Keywords: Medical Informatics, Optimization, Fuzzy Systems and their applications
Abstract: In this paper, we propose a mechanism for cancer cell differentiation therapy based on a game-theoretic rough set model with intuitionistic fuzzy set. We introduce an intuitionistic fuzzy relation with the help of fuzzy compatibility relation. The approximation space classification is controlled with a pair of intuitionistic fuzzy thresholds. It provides a flexibility to set up tolerance level depending on different requirements. The threshold parameters act as players and pay-offs are determined based on the shifting of equivalent classes from boundary region to positive or negative region.

Keywords: Medical Informatics, Virtual and Augmented Reality Systems, Human Factors
Abstract: In an effort to improve lay rescuers’ knowledge and skills in cardiopulmonary resuscitation (CPR), we developed a system that enables high-quality CPR by improving the perceptions of and skills in CPR. The proposed system can evaluate user CPR actions in real time. Particular characteristics of this system are the use of distance and pressure sensors for laypeople to achieve the necessary posture during CPR chest compression and the provision of audiovisual corrective feedback using augmented reality (AR). This system is anticipated to contribute to high-quality CPR training.

Keywords: Fuzzy Systems and their applications, System Modeling and Control
Abstract: This paper investigates the fuzzy H_{infty} filter design issue for nonlinear systems with time-varying delay. In order to obtain less conservative fuzzy H_{infty} filter design method, a novel integral inequality is employed to replace the conventional Lebniz-Newton formula to analyze the stability conditions of the filtering error system. Besides, the information of the membership functions is introduced in the criterion to further relax the derived results. The proposed delay dependent filter design method is presented as LMI-based conditions, and corresponding definite expressions of fuzzy H_{infty} filter are given as well. Finally, a simulation example is provided to prove the effectiveness and superiority of the designed fuzzy H_{infty} filter.

Keywords: Fuzzy Systems and their applications, Optimization
Abstract: Fuzzy logic systems have been extensively applied for solving many real world application problems because they are found to be universal approximators and many methods, particularly, gradient descent (GD) methods have been widely adopted for the optimization of fuzzy membership functions. Despite its popularity, GD still suffers some drawbacks in terms of its slow learning and convergence. In this study, the use of decoupled extended Kalman filter (DEKF) to optimize the parameters of an interval type-2 intuitionistic fuzzy logic system of Tagagi-Sugeno-Kang (IT2IFLS-TSK) fuzzy inference is proposed and results compared with IT2IFLS gradient descent learning. The resulting systems are evaluated on a real world dataset from Australia's electricity market. The IT2IFLS-DEKF is also compared with its type-1 variant and interval type-2 fuzzy logic system (IT2FLS). Analysis of results reveal performance superiority of IT2IFLS trained with DEKF (IT2IFLS-DEKF) over IT2IFLS trained with gradient descent (IT2IFLS-GD). The proposed IT2IFLS-DEKF also outperforms its type-1 variant and IT2FLS on the same learning platform.

Keywords: Fuzzy Systems and their applications, Expert and Knowledge-based Systems, Decision Support Systems
Abstract: The intuitionistic fuzzy set which is characterized by a membership degree and a non-membership degree, is a very powerful and useful tool to cope with fuzziness and uncertainty. Recently, the Pythagorean fuzzy set which is an extension of the intuitionistic fuzzy set has been introduced. In this paper, we focus on multi-attribute decision making with Pythagorean fuzzy information. First of all, considering the Bonferroni mean aggregation operator can take the interrelationship between arguments being fused into account, we introduce some Bonferroni mean-based aggregation operators for fusing Pythagorean fuzzy information. Then, a novel approach to multi-attribute decision making problems is proposed and discussed. Finally, an instance of supply chain management is provided to illustrate the validity of the new approach.

Keywords: Neural Networks and their Applications, Fuzzy Systems and their applications, Fuzzy Systems and Evolutionary Computing
Abstract: We present a deep learning architecture for learning fuzzy logic expressions. Our model uses an innovative, parameterized, differentiable activation function that can learn a number of logical operations by gradient descent. This activation function allows a neural network to determine the relationships between its input variables and provides insight into the logical significance of learned network parameters. We provide a theoretical basis for this parameterization and demonstrate its effectiveness and utility by successfully applying our model to five classification problems from the UCI Machine Learning Repository.

Keywords: Image Processing/Pattern Recognition, Fuzzy Systems and Evolutionary Computing, Machine Learning
Abstract: In this paper, a fast, transparent, self-evolving, deep learning fuzzy rule-based (DLFRB) image classifier is proposed. This new classifier is a cascade of the recently introduced DLFRB classifier called MICE and an auxiliary SVM. The DLFRB classifier serves as the main engine and can identify a number of human interpretable fuzzy rules through a very short, transparent, highly parallelizable training process. The SVM based auxiliary plays the role of a conflict resolver when the DLFRB classifier produces two highly confident labels for a single image. Only the fundamental image transformation techniques (rotation, scaling and segmentation) and feature descriptors (GIST and HOG) are used for pre-processing and feature extraction, but the proposed approach significantly outperforms the state-of-art methods in terms of both time and precision. Numerical experiments based on a handwritten digits recognition problem are used to demonstrate the highly accurate and repeatable performance of the proposed approach.

Keywords: Human Performance Modeling, Design Methods, Robotic Systems
Abstract: A key challenge in the automatic verification of robot mission software, especially critical mission software, is to be able to effectively model the performance of a human operator and factor that into the formal performance guarantees for the mission. We present a novel approach to modelling the skill level of the operator and integrating it into automatic verification using a linear Gaussians model parameterized by experimental calibration. Our approach allows us to model different skill levels directly in terms of the behavior of the lumped, robot plus operator, system. Using MissionLab and VIPARS (a behavior-based robot mission verification module), we present a comparison of our predicted performance guarantees for two missions in which a teleoperated quadrotor identifies a target for an autonomous ground robot to intercept: one mission in which the operator flies the quadrotor by line of sight to locate the target and one where the operator flies the quadrotor using its video feed. We demonstrate the effectiveness of our approach by comparing predicated performance to experimentally measured performance.

Keywords: Human Performance Modeling, Human Factors
Abstract: The energy consumption of commercial and business sector has rapidly increased and saving energy in office building has been encouraged. However, it may not only affect comfort of office workers but also give negative effect on their intellectual productivity. So it is important to evaluate and keep or improve intellectual productivity and authors have been developed the quantitative and objective index of intellectual productivity. In this study, a new working state model including the idea of concentration depth and new index MCTR and CDI were developed from the proposed model. These new index were confirmed by the experiment of varied motivation and data analysis of the past experiment.

Keywords: Human Performance Modeling, Human Factors, Human-Computer Interaction
Abstract: Fitts' law is an empirically derived model that describes movement duration during human arm reaching as a function of movement distance and target width. Although this law does not consider dynamic properties, such as motor commands and joint torques, it can explain the speed-accuracy trade-off characteristics of human arm movements in most cases. However, human arm movements are achieved by transforming motor commands through dynamics. Thus, speed-accuracy trade-off characteristics can be explained by the joint torque produced by motor commands. Here, we investigated whether the speed-accuracy trade-off described by Fitts' law can be better explained by joint torque, which is directly controlled by motor commands. To examine the relationships between the movement speed, end-point accuracy, and joint torque, we performed temporally and spatially constrained experiments. A positive correlation was observed between the integrated absolute torque and end-point error, which is a measure of end-point accuracy for the trial-averaged values of each experimental condition. These findings suggest the possibility that the speed-accuracy trade-off described by Fitts' law can be explained by human arm dynamics and its parameters.

Keywords: Human Performance Modeling, Human Factors, Human-Machine Cooperation & Systems
Abstract: This paper explores the predictive power of perhaps the most well-supported human performance model in the context of a complex ecological task. The model is Fitts’ Law, which describes the classic speed-accuracy tradeoff of goal-directed motor behavior. The task is modern pistol shooting competition, which demands explicit cognitive strategy and full-body biomechanical coordination. Data obtained via video analysis indicate that Fitts’ Law can in fact predict human performance in competitive shooting. Speed-accuracy tradeoffs for target transitions are further investigated to determine an optimal pace for competitive shooting in order to maximize score. A Monte Carlo simulation is also offered which develops a probability distribution of possible scores based on accuracy and pace, all informed only by a calibrated Fitts model.

Keywords: Human Performance Modeling, System Modeling and Control, Decision Support Systems
Abstract: The selection of an appropriate sequence of activities is an essential task to keep student motivation and foster engagement. Usually, decisions in this respect are made by taking into account the difficulty of the activities, in relation to the student's level of competence. In this paper, we present a dynamic model that aims to predict the average performance of a group of students at solving a given series of maths problems. The system takes into account both student- and task- related features. This model was built and validated by using the data gathered in an experimental session that involved 64 participants solving a sequence of 26 arithmetic problems. The data collected from the first 16 problems was used to build the model, and the remainder were employed to validate it. Results show a correlation with r=0.59 between the real and predicted scores, and support the effectiveness of the model at anticipating the students' performance over a sequence of tasks.

Keywords: Fault Monitoring and Diagnosis, System Modeling and Control, Optimization
Abstract: In this paper we develop a non-intrusive model-based catalyst monitoring algorithm that operates by determining the magnitude of the catalyst's frequency-domain transfer function in a specific range of frequencies corresponding to a small-amplitude square-wave input command. This method requires the calibration of two parameters within a simple catalyst model consisting of a system gain, a time delay, and an integrator. This method for catalyst monitoring offers several advantages over current methods. Specifically, it is robust to catalyst downstream oxygen-sensor location, does not require any new hardware, and operates non-intrusively in a semi-continuous manner. Thus, the method does not require restrictive steady-state entry conditions or specific events such as deceleration fuel cut-off to operate. Results obtained over a statistically significant number of varied drive cycles demonstrate the ability of the catalyst monitor to accurately detect the presence of a degraded catalyst.

Keywords: Fault Monitoring and Diagnosis
Abstract: For modern industrial processes, timely detection of incipient faults is of vital importance so as to ensure safe and optimal process operation. Though recently statistical process monitoring (SPM) has been extensively studied and widely applied in practice, conventional multivariate statistics are usually not sensitive to incipient faults. In this paper, a new multivariate statistical index called augmented Mahalanobis distance (AMD) is proposed for incipient fault detection. It can be concluded from fault detectability analysis that the AMD index is more sensitive to incipient faults than the conventional Mahalanobis distance (MD) index. Besides, the idea of augmentation utilized in the AMD index can also be applied to some other SPM models. Finally, case studies on a numerical example and the continuous stirred tank heater (CSTH) process are conducted to demonstrate the effectiveness of the proposed AMD index, in comparison with the MD index, as well as the squared prediction error (SPE) and T-square indices.

Keywords: Intelligent Power Grid
Abstract: This paper investigates the uncertainty of the day-ahead distribution system scheduling considering the random variations of both Photovoltaic-based distributed generator (PV-DG) output power and load. Instead of Monte-Carlo simulation (MCS), a two-point estimation method (2PEM) is applied to obtain accurate and computation-efficient analysis results. Based on the two-year real-world hourly weather and load data in the city of Ottawa, the estimation accuracy of the 2PEM has been verified in an equivalent 44 kV distribution feeder system. In terms of computational efficiency, the 2PEM can significantly reduce the computation burden with comparison to MCS. By using the 2PEM, the impact of PV-DG output power and load variations on the uncertainty of the distribution system scheduling under different seasons is thoroughly studied. The analytical results show that the range of standard deviation of optimally scheduled DG generation for this distribution feeder system is larger in summer than that in winter.

Keywords: Fault Monitoring and Diagnosis, Intelligent Power Grid, Cooperative Systems and Control
Abstract: Voltage magnitudes in transmission power systems must be kept within the limits defined by regulatory agencies for safe operations. Thus, this paper proposes an approach to determine and apply a sequence of adjustments to control the voltage magnitude in such systems. The adjustments follow two methodologies based on a reduced Jacobian matrix (JQV ) of the system power balance equations. Computational simulations made in the IEEE (Institute of Electrical and Electronic Engineers) 57-bus system evaluated the proposed approach for operational scenarios with voltage magnitude violations. The results obtained provide the reactive power dispatch to correct voltage magnitude violations, voltage profiles and active power losses as the recommended adjustments are executed.

Keywords: Computational Intelligence
Abstract: How to reduce the computation time and how to improve the quality of the clustering result are the two major research issues. Although several efficient and effective clustering algorithms have been presented, none of which is perfect. As such, an effective clustering algorithm, which is based on the prediction of searching information to determine the search directions at later iterations and employs the k-means as the local search operator to fine-tune the end result, is presented in this paper. Simulation results show that the proposed algorithm is less sensitive to the initial random solution; thus, it is capable of providing a better result than the other clustering algorithms compared in this paper in terms of the quality of the clustering result.

Keywords: Computational Intelligence
Abstract: One of the most well-known clustering methods for wireless sensor network is, no doubt, the so-called low energy adaptive clustering hierarchy (LEACH) because it is simple and easy to implement. Although LEACH tries to provide a fair selection mechanism by randomly selecting a number of sensors as the cluster-heads, it does not take into account the distribution of sensors, the main reason that LEACH is not able to allot transmissions to sensors efficiently, so it will make sensors far from the base station consume more energy in some cases. An efficient clustering algorithm to overcome this problem is presented in this paper. The proposed algorithm leverages the strength of a novel metaheuristics, search economics, and LEACH-centralized (LEACH-C) for wireless sensor network (WSN). Simulation results show that the search economics based clustering algorithm is capable of not only prolonging the lifetime of a WSN but also providing a balance strategy for the energy consumption of sensors in a homogeneous WSN.

Keywords: Computational Intelligence, Cybernetics for Informatics
Abstract: A novel method with M-sequence code in optical code-division multiple-access (OCDMA) network, called pseudo-random number mapping/coding (PRNMC) algorithm, includes chaos equation, HCC/EHCC algorithm, two mapping methods. An approximately symmetric scheme is used to transmit and receive the secret key in private channel from encoder to decoder. By combining those algorithms appropriately, the security of network is increased and reduces the probability of eavesdropping of codeword.

Keywords: Expert and Knowledge-based Systems, Computational Intelligence
Abstract: Different from full periodic patterns, partial periodic patterns could ignore the occurrence of some events in time positions. In this paper, we have presented a gradually pruning algorithm (GPA) for reducing the number of candidate patterns in the mining process. It is based on the two-phased periodic utility upper-bound (PUUB) model and could avoid information loss. Compared to the original approach without gradually pruning, the one proposed here could reduce the execution time but get the same desired results.

Keywords: Neural Networks and their Applications, Knowledge Acquisition in Intelligent, Computational Intelligence
Abstract: Recently, the market on deep learning including not only software but also hardware is developing rapidly. Big data is collected through IoT devices and the industry world will analyze them to improve their manufacturing process. Deep Learning has the hierarchical network architecture to represent the complicated features of input patterns. Although deep learning can show the high capability of classification, prediction, and so on, the implementation on GPU devices are required.We may meet the trade-off between the higher precision by deep learning and the higher cost with GPU devices. We can success the knowledge extraction from the trained deep learning with high classification capability. The knowledge that can realize faster inference of pre-trained deep network is extracted as IF-THEN rules from the network signal flow given input data. Some experiment results with benchmark tests for time series data sets showed the effectiveness of our proposed method related to the computational speed.

Keywords: Fuzzy Systems and their applications
Abstract: The paper proposes a data mining method to find the relationships between fan page users’ sentiment and customers’ purchase behavior in order to predict those customers’ purchase intention in the future. The business companies create their own fan pages and post advertisements to prompt their products. The fan page users always post their opinions on the wall to tell the feelings about products. Since all those opinions will be spread to every corner in the social network, some marketing managers would wonder whether those opinions help or harm the products sale. If we can measure the sentiment of users’ opinion and then find the relationships between users’ sentiment and products sales volume, the discovered sentiment-sales patterns can be used to predict their customers’ future purchase intention. In this study, a framework based on fuzzy set model and association rule mining is proposed to find sentiment-sales patterns. First, the specific sentiment topics with their related terms need to be defined. Then the fuzzy membership functions for the terms are used to evaluate fan page users’ sentiment score. Assuming the products sales volume information is released from the company, and we can use inter-transaction association rule mining method to find the sentiment-sales patterns which reveal the relationships between fan page users’ sentiment and customers’ purchase behavior. A theoretical experiment is given to illustrate how the proposed framework works.

Keywords: Machine Vision, Image Processing/Pattern Recognition
Abstract: In this paper, a robust visual tracking system with occlusion handling is proposed to track the target with real-time performance. The thermal camera, which can observe the heat originated from the target such as the human body or vehicle, can collaborate with the color camera to track the target in the cluttered environment or under occlusion. Unlike the general tracking by using the color camera and the thermal camera, which simply verifies the target hypotheses in these two kinds of image domains, a sampling multiple importance resampling scheme is proposed here to efficiently generate the hypotheses and verify them. The better hypotheses in the color and thermal images are selected to evaluate the sparse appearance representation such that the target under severe occlusion can be identified with real-time performance. Using this resampling scheme, the diversity and the convergency are simultaneously considered by adaptively fusing the hypotheses in the color and thermal images. Moreover, the updating strategy of target image model is designed by estimating the occlusion ratio and the environmental similarity such that the robustness of tracking can be greatly increased. Finally, the proposed approaches have been validated in several scenes to present the tracking performance.

Keywords: Assistive Technology, Human-Machine Cooperation & Systems, Smart Sensor Networks
Abstract: The current populace of the elderly is apparently abandoned by the younger generations due to their individual circumstances. To heighten the vitality and strengthen the fitness of elders, assisting a home care system can be an admittance that provides comprehensive nursing and monitoring them in the regular interim. To deliver an interactive service supervision platform to the elders a smart environment of various sensors are clubbed together to establish an intuitive platform that can control the home appliances and gadgets within the living space of elders. The proposed system used voice and gesture (MPU6050 accelerometer) to control the home appliances like turning on/off the light, closing/opening of curtains, TV, and fan or AC within the living spaces. The system also monitors the real-time activity like heart rate and body temperature for the elderly citizens. In the case of emergency, for instance, anomalous behaviors like heart stroke occurs, the proposed system set-up triggers an alarm and the emergency bulb will be strikes “on” to alert their kin. This smart environment can set the temperature and help control the living parameters based on the users’ comfort and their health conditions. The whole design is to provide modest support systems for the elder to live healthily and safely in an independent living environment.

Keywords: Machine Vision, Image Processing/Pattern Recognition, Medical Informatics
Abstract: To successfully increase athletes’ or exercisers’ fitness and endurance, the factors of physiological signal, emotion, or the level of fatigue should be considered during the training program. Many clinical decision support systems can assist to monitor the exercisers by some wearable devices. And, the questionnaire should also be taken into account to produce a report. Such process is cumbersome, and the results are not objective. Furthermore, one may feel uncomfortable when wearing the devices during the training program. In this research, the Rating of Perceived Exertion (RPE) is expected to be estimated automatically without any wearable devices and questionnaires. A camera based heart rate detection algorithm and a fatigue expression feature extractor are fused to estimate the RPE value. The results show that our hear rate detection algorithm can be competitive to the wearable devices, and the trend of the detected heart rate is correlated to RPE. Moreover, the fatigue feature can help reduce the error of the estimation.

Keywords: Wearable Computing, Smart Sensor Networks, Computational Life Science
Abstract: PM (Particulate Matter) 2.5 has been shown that will affect seriously heath of people. Many countries deployed various air pollution detection devices in order to report concentration of PM 2.5 and to show how much seriousness of air pollution is. But, more important is how much PM 2.5 has been inhaled to people anytime and anywhere. Therefore, in this paper, we propose a method for monitoring and estimating people’s PM 2.5 inhalation by using personal physiological data, such as heart rate (HR), and mobile PM2.5 sensor. We can retrieve people’s heart rate from company’s cloud platform of smart bracelet and then calculate his/her PM2.5 inhalation based on personal HR and minute ventilation (VE). In the method, we first adopt Bruce protocol to measure various function of body, such as HR and VE, on a treadmill and exploit regression model to build predictive model for VE. Therefore, we can utilize smart bracelet to monitor people heart rate and then after that calculate PM2.5 inhalation based on personal HR and mobile PM2.5 sensor (MPS). We think that the method can effectively estimate the PM 2.5 inhalation of physical activity.

Keywords: Human-Machine Cooperation & Systems, Human Factors, Assistive Technology
Abstract: Emerging technologies in the field of automatization meanwhile enable partially and highly automated vehicles in the aviation and automotive domains, where the human operators are assisted or (partially/temporarily) replaced in their tasks by advanced automation systems. Nevertheless due to technological limitations and ethical reasons, full autonomous vehicles in both domains might not be realizable in the near future. Instead system designs, which enable shared and cooperative guidance and control of vehicles by human operators and automation systems could be more feasible solutions. This paper sketches a common framework of shared and cooperative control that describes the two concepts not as different but as coinciding concepts for the shared intentionality, control and cooperation between humans and machines. A brief overview off developed shared and cooperative control designs in the aviation and ground vehicle domain is given. Finally a brief outlook is displayed for a possible universal language in shared and cooperative guidance and control.

Keywords: Human-Machine Cooperation & Systems, Design Methods, Cooperative Systems and Control
Abstract: In highly dynamic domains like mobile robotics, it is essential to keep human in the control loop of the process and to maintain his/her situation awareness through adequate levels of automation. Our paper is focused on how to better match human and machine capabilities defining adaptive levels of automation. A method based on human-machine cooperation concepts which allow designing different possible human-machine interactions is used in order to identify different adaptive levels of automation. We present our approach to control the cooperation among the agents on use cases in the crisis management domain with firefighters and robots. Three types of agents take place in the scenario, human supervisor, firefighter with smart garment and robots. At the operational level, the robots and firefighter have to cooperate together and with the human supervisor in order to achieve a common goal. The human supervisor is at the tactical level; he/she can observe the situation, make decision about the process and send instructions to the robots using a visual support in which large amounts of information are presented. The proposed approach helps the agents to better organize their cooperative actions.

Keywords: Human-Computer Interaction, Cooperative Systems and Control, Intelligent Transportation Systems
Abstract: With new technologies in the area of assistance and automation on the market, the dream of driving in automated vehicles becomes reality. While certain research areas predict fully autonomous vehicles in the near future, a more feasible composition still has a driver, at least as a back-up solution, operating the vehicle in certain situations with certain degrees of control, cooperating with the automation. In such complex highly automated human machine systems it is necessary to elucidate responsibilities of automation and human and assert controllability. To do so, a usable interaction design is required to support drivers in their driving tasks while maintaining the necessary controllability. This paper presents the concept of interaction patterns to improve usability and controllability when switching between different modes of automation. An interaction pattern implements image schemas to create intuitive interaction between a human and a computer. A study with highly automated truck convoys was carried out and the usability and controllability when switching between modes was evaluated.

Keywords: Human Factors, Assistive Technology, User Interface Design
Abstract: Many novel physical assistance devices are beginning to incorporate intelligent robotic systems and mechatronic components. In terms of a human-centered design it is crucial to assess the perceived subjective usability and acceptance of these systems. A questionnaire was thus designed to evaluate novel physically assisting devices in order to support developers in their design decisions as well as users during individualizing of their assistive devices. Two studies (n1 = 9, n2 = 21), using two different devices, were conducted to analyze objectivity, reliability, and validity. The results show an overall high internal consistency (Cronbach’s α > 0.8), which indicates reliability and applicability of the QUEAD. Criterion validity was tested applying correlations with established objective measures for efficiency (time to task completion), effectivity (errors and collisions), and commitment (mean force). Construct validity was applied using a proposed model and correlations to verify convergence. The results show that the QUEAD is able to assess perceived usability and acceptance.

Keywords: Human Factors, Human-Machine Cooperation & Systems, Assistive Technology
Abstract: Visual field defects, which are partial losses of the visual field, may have an impact on driver behavior. They affect the driver’s information processing and are a possible cause of traffic accidents. Some patients who suffer from optic diseases related to visual field defects try to compensate for their disability by more actively moving their head in order to look around more carefully. Compensation is a driving strategy used to maintain safe driving regardless of the driver impairment. Several studies have shown that compensation is effective at enhancing the driving performance. However, few studies have examined both the compensation of drivers who have advanced visual field defects, and a quantitative analysis of driver performance while driving under such compensation. For these reasons, by using a driving simulator and eyeglasses that can imitate advanced visual field defects, this study investigates driver compensatory head movements to better understand the extent to which they are effective in avoiding pedestrian collisions. The results indicate that active head movements are efficient at reducing the number of pedestrian collisions compared with driving without such compensation. However, they are insufficient in terms of collision avoidance when compared to driving without a visual impairment. In other words, the results imply that there are assorted unavoidable circumstances that occur even when the driver attempts to compensate their visual impairment as much as possible.

Keywords: Human-Machine Cooperation & Systems, Supervisory Control, Human Factors
Abstract: In order to realize really useful Level 2 driving automation systems that can be used in urban areas, it is a vital issue to develop a human-machine interface that assures drivers are able to recognize when to intervene into control. Visual information may not be appropriate for this purpose because the driver is required to monitor the traffic environment and the system status continuously. In this paper, we propose a driving automation system that performs a kind of “avoiding” maneuver against a hazard upon detection of the hazard. We expect that such avoiding maneuver makes a driver understand that the system has detected the hazard. Missing of such avoiding maneuver suggests the detection failure. We conduct an experiment with a driving simulator in order to examine whether such avoiding maneuver is really useful for drivers to understand the system status. The results suggest that it is actually useful if drivers hold the steering wheel. If, on the other hand, driver’s hands are off the steering wheel, it tended to be difficult to recognize the system’s failure.

Keywords: Smart Sensor Networks, Optimization, Decision Support Systems
Abstract: This paper deals with the smart placement of motion sensors in smart homes for Ambient Assisted Living, by considering the sensor technology and cost and respecting specific coverage requirements. The core of the proposed methodology is a decision module that can optimize the sensors placement according to different objectives. More precisely, the main objective is the minimization of costs of the deployed sensors. Moreover, the second objective can be the maximization of the overlapping in order to find a robust solution or the minimization of the overlapping of the detection areas in order to improve the inhabitant localization. A case study demonstrates the effectiveness of the proposed strategy on sensors placement in a domestic environment.

Keywords: Biometric Systems and Bioinformatics, Computational Intelligence, Fuzzy Systems and their applications
Abstract: The application of the Soft Computing based methods, especially, the Tensor Product (TP) transformation has several beneficial properties from the biological modeling and control point of view, because complex, nonlinear processes can be handled by them effectively. Another advantage of these tools consist on the Linear Parameter Varying (LPV) and Linear Matrix Inequality (LMI) based techniques can be easily connected to them. The aim of this study is to develop TP models, which can describe the tumor growth beside anti-angiogenic treatment. The role of the anti-angiogenic therapies is to decrease the size of the tumor to operable or maintainable level. From control engineering point of view, the treatment process can be formulated as a control task. In this work, we realized two TP models, which approximates the initial transformed model with high accuracy, regardless the kind of input load and without stability problems. The TP models will be used for TP-based controller design on LMI basis.

Keywords: Computational Intelligence, Computational Life Science, Hybrid models of NN
Abstract: Science of Neural Networks, and even much more so computing applications, have undergone developments beyond any predictions since McCullock-Pitts artificial neuron (1943) up via Hopfield’s neurons (1982, 1984) to Kasabov spiking-neurons neucube (2014) and evolving connectionist systems (2003). Still computational functionality of all kinds of neural network implies guaranteed operating steady-state equilibrium is fast-reached first. On the other side of this spectrum Science of Neurophysiology yielded insights converging to Systems Biology approach Gayton-Hall (2006). It appeared, on the crossroad of these findings with Kolmogorov’s representation superposition and Hilbert’s Thirteen problem certain rater delicate subtle issues emerged Sprecher (2017). This paper gives one perception of these issues and suggested a revised view on the foundations of past developments, possibly by re-thinking own stability results for recurrent neural networks which possess time-varying delays.

Keywords: Computational Life Science, Artificial Life, System Modeling and Control
Abstract: The estimation of the domain of attraction of a class of susceptible-infectious-removed-susceptible immigration is investigated. On assumption the disease-free equilibrium and the endemic equilibrium existences, hence a Lyapunov function too, the domain of attraction of the epidemic model is estimated by means of LF-LMI-moment and SOS optimization approaches. An invariant subset of the domain of attraction, along with certain enlargement, has been achieved. Simulation results, given in a comparison presentation, demonstrate feasibility and validity of the proposed technique as well as reveal that this algorithm outperforms other ones in applications to epidemic models.

Keywords: Expert and Knowledge-based Systems, Machine Learning
Abstract: Most news recommendation method focus on using textual information of news to solve data sparseness problem of collaborative filtering, while when the knowledge from the text is not enough, these method can’t work well, a collaborative model combines matrix factorization, topic analysis and knowledge graph representation is proposed by introducing the knowledge from external knowledge base to alleviate the deficient of the text, experiment on real life news data set shows that the joint model outperform the state-of-the-art method by 14% in Recall@200 metric, and improved the recommendation on sparse item by 20%.

Keywords: Machine Vision, Machine Learning, Neural Networks and their Applications
Abstract: Building a modern Optical Character Recognition (OCR) system for Chinese is hard due to the large Chinese vocabulary list. Training images for rare Chinese characters are extremely expensive to obtain. Radical-based OCR systems tackle this problem by first extracting and recognizing basic graphical components (i.e., radicals) of a Chinese character. However, how to reliably recognize radicals still remains an open challenge. In this paper, we propose a novel Radical Extraction Network (REN) to extract and recognize radicals using deep Convolutional Neural Network (CNN). REN is end-to-end trainable, and it needs less hand-tunning compared with previous segmentation-based approaches. Deep appearance models for radicals are learned from data in a weakly supervised fashion, and no radical-level annotations are required. We learn to recognize different radicals on commonly used Chinese characters, and transfer the learned deep appearance models to rarely used Chinese characters. Experimental results show that the proposed method helps the classifier to recognize rare Chinese characters.

Keywords: Machine Learning
Abstract: Numbers of samples in different classes are in nature imbalanced in many machine learning problems. Single classifier-based methods are subject to high variance. Therefore, ensemble-based methods are more suitable for dealing with imbalanced pattern classification problems. In this work, we propose a boosting-based method: BSMBoost which creates an ensemble of classifiers using samples selected by both the stochastic sensitivity measure (SSM) and the AdaBoost algorithm to yield higher and more robust performances. Experimental results show that the BSMBoost yields better and more robust performances in comparison to other state-of-the-art boosting-based imbalanced classification methods.

Keywords: Machine Learning, Neural Networks and their Applications
Abstract: Accurately predicting driving service orders in different regions is an essential task for service companies, in order to improve the service quality. In this paper, a specific ensemble multi-view prediction framework is proposed to address this task. It ensembles several different multi-view-based models with a weighted linear combination. Specifically, we have designed three specific multi-view-based models, which of them contains two type of views. In first view, a spatio-temporal prediction model (ST-Model) is employed to construct the features on historical orders. In second view, a specific CRF is designed to joint adjacent regions to collaborate predict future orders in these regions. The two views are learned and inferred simultaneously. Extensive evaluations on real order data in Beijing show that the proposed framework outperforms all baselines and participated multi-view-based models significantly in terms of mean absolute error (MAE) and root mean square error (RMSE).

Keywords: Agent-Based Modeling, Artificial Life, Expert and Knowledge-based Systems
Abstract: Defense modeling and simulation (DM&S) offers insights into the efficient operations of combat entities, e.g., soldiers and weapon systems. Most DM&S aim at exact description of military doctrines, but often the doctrines fails to provide detail action procedures about how the combat entities conduct military operations. Such unspecified descriptions are filled with the rational behaviors of the combat entities in a battlefield, and thereby the combat effectiveness from these combat entities would differ. Also, by incorporating such rational factors, this could provide the insights that cannot be captured from the traditional works. To examine this postulation, this paper developed a computer generated force where the tactical maneuver of combat entities are realized by the combination of descriptive and prescriptive modeling. Specifically, the descriptive models describe the explicit action rules in military doctrines, and they are modeled using discrete event system specification (DEVS) formalism; the predictive models denoted the rational behavior of the combat entities under the military doctrines, and they are modeled using partially observable Markov decision process (POMDP). The provided results illustrated that the proposed approach helps to maintain a team formation effectively, and this formation maintenance lead to the better combat efficiency.

Keywords: Machine Learning, Neural Networks and their Applications, Computational Intelligence
Abstract: Deep multi-layer neural networks are generally trained using variants of the gradient descent based algorithm. However, this kind of algorithms usually encounter a series of shortcomings, such as low training efficiency, local minimum, difficult control parameter tuning, and gradient vanishing or exploding. Besides, for a specific application, how to design the structure of the network, that is, how many neurons in each hidden layer and how many hidden layers is needed, is also a very tricky problem and is usually solved by trial and error in practice. To overcome the shortcomings mentioned above, we present a fast and fully automated method to train stacked autoencoders based deep neural networks in this paper. The proposed method trains the stacked autoencoders adopting the pseudoinverse learning algorithm with the low rank approximation. The entire training process neither need to set the learning control parameters, nor specify the number of hidden layers and the number of neurons in each hidden layer. The experimental results show that the proposed method can achieve a comprehensively better performance in terms of training efficiency and accuracy.

Keywords: Machine Learning, Optimization
Abstract: Predicting an approval rate of politicians is a popular task. While a type of prediction is using a text mining from news articles, we introduce a text augmented Gaussian process to perform the prediction with contexts. We test our model with 2017 South Korea Presidential Election in 1) a quantitative evaluation, and 2) a qualitative analysis. The performance of the model with text input is better than the performance of the model without the text input, which has been a typical approach of applying the Gaussian process. Moreover, the model can capture keywords which provide behind rational of the prediction result, which was not provided with only temporal information.

Keywords: Biometric Systems and Bioinformatics
Abstract: A symptom is the physical indication of an unstable state or the beginning of diseases. Symptom analysis is an essential factor in the medical area, where it is used for disease diagnosis, drug prescription, and the development of new pharmaceuticals. Commensurate with its importance, symptom analysis has been the subject of various studies in recent years. However, prior literature on this topic has been largely limited to studying symptoms for a specific disease. Our paper attempts to expand and build on previous studies by introducing a network-based symptom analysis. Symptom analysis that can provide a basis for analyzing symptoms related to various diseases. For a universal symptom analysis system, we proposed a network-based symptom analysis. In order to construct a symptom network, we utilized Medical Subject Heading (MeSH) terms and the PubMed search engine which are maintained and developed by the National Center for Biotechnology Information (NCBI) at the National Library of Medicine (NLM). We identified symptom-disease relationships with two measurement, the term frequency-inverse document frequency (TF-IDF) and frequent occurrence of two terms (co-occurrence) from PubMed articles. Symptom-symptom pairs, which is the outline for symptom network, were built up based on symptom-disease relationships. As a result, we constructed a symptom network with 223 nodes and 5313 edges. Evaluations were performed in two ways, compared with two symptom clusters and demonstrated with previous researches. Additionally, proposed method has shown possibility for a guideline of clinical demonstration and a discovery of potential symptoms pair.

Keywords: Machine Vision, Machine Learning, Artificial Life
Abstract: One main difficulty in applying action recognition to practical applications is the need to segment beginnings and ends of actions in a continuous online monitoring process. This paper proposed a finite state machine (FSM) model for automatic action segmentation and recognition solution, based on pose streams in the form of skeleton joint data provided by Kinect. With the action recognition problem reframed as a state identification problem, the key solution to state identification hinges on detection of changing events, which signify the start of new action and the recognition of the underlying action. In that regard, a decision tree is constructed to detect these events based on the spatial positions and the changes of the skeleton data. In addition, to identify the current state or equivalently the action of a detected person, a fault observer is derived from the modeled action FSM. The fault observer does not only identify the initial state of action when the recognition process starts, but also serve the purpose of error recovery when the system loses track of ongoing events at times of intermittent sensor faults. Additionally, an AutoCorrect mechanism is presented to further enhance the accuracy of action recognition. To evaluate the proposed approach, an experiment with 300 participating subjects has been conducted for a total of 900 test sequences. The 98.63% correct identification result ensures the proposed approach a promising solution to constant action monitoring solution.

Keywords: Neural Networks and their Applications, Machine Learning
Abstract: Dropout is a technique widely used for preventing overfitting while training Deep Neural Networks. However, applying dropout to a neural network typically increases the training time. This paper proposes a different dropout approach called controlled dropout that improves training speed by dropping units in a column-wise or row-wise manner on the matrices. In controlled dropout, a network is trained using compressed matrices of smaller size, which results in notable improvement of training speed. In the experiment on feed-forward neural networks for MNIST data set and convolutional neural networks for CIFAR-10 and SVHN data sets, our proposed method achieves faster training speed than conventional methods both on CPU and GPU, while exhibiting the same regularization performance as conventional dropout. Moreover, the improvement of training speed increases when more number of fully-connected layers are used. As the training process of neural network is an iterative process comprising forward propagation and backpropagation, speed improvement using controlled dropout would provide a significantly decreased training time.

Keywords: Machine Learning, Fuzzy Systems and their applications
Abstract: A hybrid sampling technique is proposed by combining Complementary Fuzzy Support Vector Machine (CMTFSVM) and Synthetic Minority Oversampling Technique (SMOTE) for handling the imbalanced classification problem. The proposed technique uses an optimised membership function to enhance the classification performance and it is compared with three different classifiers. The experiments consisted of four standard benchmark datasets and one real world data of plant cells. The results revealed that implementing CMTFSVM followed by SMOTE provided better result over other FSVM classifiers for the benchmark datasets. Furthermore, it presented the best result on real world dataset with 0.9589 of G-mean and 0.9598 of AUC. It can be concluded that the proposed techniques work well with imbalanced benchmark and real world data.

Keywords: Neural Networks and their Applications, Agent-Based Modeling, Computational Intelligence
Abstract: Traffic congestion is a serious global problem. Enhanced or deep Q learning algorithms were applied to a traffic simulation study. The enhanced Q learning was based on a repeated local search algorithm, and it was able to find optimal pathways under a multi-agent system. Deep Q learning was also capable of learning a suitable strategy, considering dynamic changes in traffic circumstances at a highway junction. In particular, the target network of the Q learning realized a stable regulation of the loss function. This intelligent method based on deep reinforcement learning could become an effective tool to optimize car pathways including an autonomous driving system.

Keywords: Neural Networks and their Applications, System Modeling and Control, Consumer/Industrial Applications
Abstract: Deep learning has been proposed for soft sensor modeling in process industries. However, conventional deep neural network (DNN) is a static network and thereby can not embrace evident dynamics in processes. Motivated by nonlinear autoregressive with exogenous input (NARX) model and neural nets based dynamic modeling, a dynamic network called NARX-DNN is put forward by further utilizing historical process samples and quality samples in a period of time. A modified hyper-parameter tuning method is proposed to choose optimal hyper-parameters of NARX-DNN with little manual intervention, which automatizes the training procedure and reduces computational cost. The quality prediction error of validation data is interpreted from different aspects, and the most appropriate delay of historical data can be determined automatically. The effectiveness of the proposed method is validated by case studies on a sulfur recovery unit and a debutanizer column. As training, validation and test data sets are selected by the original orders of data samples, the accurate prediction results of NARX-DNN demonstrate its ability in dealing with operation condition changes which are common in real processes.

Keywords: Neural Networks and their Applications, System Modeling and Control, Control of Uncertain Systems
Abstract: This paper applies a recurrent higher-order neural network for sliding-mode pinning control of complex networks for achieving trajectory tracking. This control strategy does not require having the same coupling strength for all node connections on the network. The tracking effectiveness and dynamical behavior of the controlled network is illustrated via simulations.

Keywords: Computational Intelligence, Cybernetics for Informatics
Abstract: This paper proposes a novel hybrid model that integrates the synergy of two superior classifiers for functional magnetic resonance imaging (fMRI) recognition, namely, convolutional neural networks (CNNs) and support vector machines (SVMs), both of which have proven results in the field of image recognition. In the proposed model, the CNN functions as a trainable feature extractor and the SVM functions as a recognizer. This hybrid model extracts features from raw images and generates predictions for fMRI recognition. We conducted experiments on Haxby’s 2001 fMRI dataset. Comparisons with Haxby’s study using the same database indicated that the proposed fusion achieved superior accuracy of 99.5% compared to the Haxby’s approach. Further, when the CNN was used as a feature extractor, the SVM classifier was demonstrated to be the best combining counterpart, providing the best synergy effect in terms of accuracy. This is compared with other classifiers based on learning algorithms such as decision tree, neural network, K-nearest neighbor, random forest, and AdaBoost.

Keywords: Expert and Knowledge-based Systems, Optimization, Knowledge Acquisition in Intelligent
Abstract: Probabilistic Conditional Preference network (PCP-net) provides a compact representation of preferences characterized with uncertainty. We propose to enrich the expressive power of the PCP-net by adding constraints between some of the variables. We call this new model, the Constrained PCPnet (CPCP-net). We study the key preference reasoning task with the proposed CPCP-net which consists in finding the most probable optimal outcome i.e. the most probable outcome that best represents the preferences while satisfying all the constraints. In this regard, a variant of the Branch and Bound algorithm has been proposed and experimentally evaluated on CPCPnet instances, randomly generated based on the RB-model. The results of these experiments show that the new proposed solving method is capable of returning the most probable optimal outcome in a reasonable time.

Keywords: Neural Networks and their Applications, Image Processing/Pattern Recognition, Machine Learning
Abstract: Nowadays, more and more methods have been proposed to solve the problem of face detection based on computer implementation. Due to the variations in background, illumination, pose and facial expressions, the problem of machine face detection is complex. Recently, deep learning approaches achieve an impressive performance on face detection. In this paper, a model named Multi-Scale Fusion Convolutional Neural Network (MSF-CNN) is proposed to train the face detector. The model is trained by Convolutional Neural Network and detecting is based on the Viola & Jones detector’s sliding windows structure. Particularly, in the process of feature extraction, we adopt the design of multi-scale feature fusion with different scale convolution kernels. The results are as follows: First, the fusion of multi-scale features are rich in the characteristics of learning, and the classification accuracy is higher than the single-scale. Second, we decrease the model of complexity compared with existed methods of the cascaded CNN. Third, we achieve end-to-end learning compared with cascaded separate training. Meanwhile, the proposed model has showed that the performance of results outperforms the previous methods in some well-known face detection benchmark datasets.

Keywords: Image Processing/Pattern Recognition, Neural Networks and their Applications, Machine Vision
Abstract: In this paper, we propose a scale-invariant framework based on Convolutional Neural Networks (CNNs). The network exhibits robustness to scale and resolution variations in data. Previous efforts in achieving scale invariance were made on either integrating several variant-specific CNNs or data augmentation. However, these methods did not solve the fundamental problem that CNNs develop different feature representations for the variants of the same image. The topology proposed by this paper develops a uniform representation for each of the variants of the same image. The uniformity is acquired by concatenating scale-variant and scale-invariant features to enlarge the feature space so that the case when input images are of diverse variations but from the same class can be distinguished from another case when images are of different classes. Higher-order decision boundaries lead to the success of the framework. Experimental results on a challenging dataset substantiates that our framework performs better than traditional frameworks with the same number of free parameters. Our proposed framework can also achieve a higher training efficiency.

Keywords: Image Processing/Pattern Recognition, Neural Networks and their Applications, Machine Vision
Abstract: The strong abilities of deep learning models have been shown in the area of text detection in natural scene images.

In this paper, we introduce a new method called deep metric learning for scene text detection. We use the triplet loss [1] to replace the traditional loss function (Softmax) and learn a mapping from image regions to a compact Euclidean space where distances correspond to a measure of text similarity. By combining the CNN model with metric learning, we can make reliable binary classification between text regions and non-text ones. We show that the proposed model achieves competitive results on the ICDAR 2003, ICDAR 2011, and ICDAR 2013 datasets, with the F-measure of 0.74, 0.80, and 0.79.

Keywords: Neural Networks and their Applications, Machine Learning
Abstract: This paper presents one step toward creating the building blocks for machine intelligence that is inspired by its biological equivalent. The authors’ quantum learning methods (deep quantum learning) are applied to quantum devices whose quantum bit (q-bit) activity is deliberately chosen to mimic the spiking behavior of biological neurons. Because of the “quantum” scale of these computers, these studies may lead to quantum hardware (rather than simulation) with enough processors and enough connectivity that can more closely mimic biological intelligence.

Keywords: Virtual and Augmented Reality Systems, Human-Machine Interface Web, Human-Computer Interaction
Abstract: With the advance of mobile technologies, virtual reality (VR) is coming to every corner of our life. The technology presents a major opportunity for retailers as they lure fickle shoppers to visit their virtual stores, particularly since modern consumers have shifted more of their buying habits online. Currently, merchants face the challenge to weed out malicious software from legitimate users to protect their online store. This paper presents a proof-of-concept technique to prevent abusing of a merchant’s online resources in a virtual environment. The technique exploits the large gap in ability between humans and software programs in spatial interaction while current methods determine whether or not a user is human by conducting various challenge-response tests based on reading. We design and implement a prototype system which demonstrates that the novel technique is capable of discriminating computerized interaction from real human input actions. The new technique improves user experience in virtual environment and system reliability by tackling the inaccessible-by-design nature of existing solutions in 2D interaction.

Keywords: Multimedia Systems, Systems Safety and Security, Consumer/Industrial Applications
Abstract: A system-on-chip field gate programmable array (FPGA)-based video processing platform for human detection in complex scenes is presented. This study details the hardware-based implementation of a human detection algorithm in 2D/3D scenes, including the capture, video processing, and display stages. The proposed method is implemented by extending a previously proposed method that uses features extracted from the Riemannian manifold of region covariance matrices computed from 2D data. The proposed method considers both 2D and depth data (3D). The LogitBoost classifier is employed to detect humans. The proposed implementation uses minimal resources and employs a pipeline technique for better performance and operation.

Keywords: Virtual and Augmented Reality Systems, Image Processing/Pattern Recognition, Neural Networks and their Applications
Abstract: A myoelectric prosthesis, which can be used as a replacement for a person’s upper limb, is able to control many hand motions optionally via surface electromyography (sEMG). Although many researchers have developed myoelectric prostheses that realize various motions, evaluation of their practicality has only been carried out on small numbers of patients. To solve this problem, a myoelectric prosthesis simulator that is able to move like a real prosthesis is needed. In this study, such a simulator that enables persons to grasp virtual objects with virtual prostheses was developed using Augmented Reality (AR). The results of comparative experiments conducted to evaluate the developed system using a pick and place task show that although it is not at present as effective as real prostheses, a virtual prosthesis is able to grasp virtual objects in the proposed simulator.

Keywords: Human-Computer Interaction, Human-Machine Cooperation & Systems, Machine Learning
Abstract: Similarity-based recommender systems can be used to pre-compute distance between item pairs, and then to quickly recommend similar items to users. The content-based approach to similarity uses the item’s description, which in movies could mean genre, director or cast. These similarity methods are often built with unsupervised learning, which means the notion of similarity is defined by those who write the method. This notion may not match that of the users, resulting in poor user experience. In this paper we used user-contributed labels representing perceived similarity between movies to build a supervised content-based (CB) model for movie recommendations. Our user study shows that the CB method with human perception factored in was significantly preferred over the CB model without.

Keywords: Human Performance Modeling, Human Factors
Abstract: In this paper, we propose a computational modeling method to investigate head-eye coordination in face-to-face behavior. The method looks into probability density of individuals' head orientation during looking at others' face. We conducted experiment under two different scenarios in human-human interaction. Under each scenario, individuals' head orientation could be fitted with one Gaussian distribution. Referring to the model, it is possible to calculate several ranges of head orientation, which could be used as surrogate for estimating visual focus of attention. The model also provides theoretical support to the design of automatic systems that measure face-to-face interaction.

Keywords: Interactive and Digital Media, Multimedia Systems, Human-Computer Interaction
Abstract: We present a method to assist pre-touch on multi-touch surfaces using features extracted from the fingertips of the user’s hands. Pixel area a feature obtained from the contour of a fingertip is computed and tracked using commodity cameras to obtain the velocity of approaching fingers. We target sound volume control for digital multi-touch instruments an area where pre-touch is demonstrated with our approach to approximating velocity of finger taps. We explore other areas of application with velocity and how it can help anticipate user actions in mobile touch displays. In order to evaluate the effectiveness of the proposed system, a system prototype was presented to users. We confirmed the satisfactory results by performing the recognition rate experiment for measuring the blob size according to the touch speed. We have demonstrated that measuring blob area size over time is a good estimate for velocity of approaching fingers. Using proximity sensors to measure the change of distance over time works well with single objects but not so well with multiple objects like fingers and lacks the richness that blob features can give us. While we tested this approach using one finger our method can easily extend to using multiple fingers.

Keywords: Wearable Computing, Assistive Technology, User Interface Design
Abstract: Predicting hand gestures and finger movements include a wide range of applications in different fields such as human computer interaction, rehabilitation, and prosthesis control. Research in this area, focuses on hand gesture classification which limits the ability of the system to a set of predefined gestures and cannot control the fine finger movements. Force Myography (FMG) is a novel method in which the volumetric change of the muscles associated with a functional motor function is measured. In this study, the feasibility of using the FMG signals for predicting fine finger movements, and the effect of the hand movement on the prediction is investigated. To obtain the FMG signals an array of 16 Force Sensing Resistors (FSR) has been utilized. To record the finger movements’ trajectory eight calibrated infrared cameras were used. Ten reflective markers, were placed on the index and middle fingers, the thumb and the back of the hand. The FMG signals and the markers’ locations are collected during performing three different hand gestures, while the participant placed their hand in three different predefined locations parallel to the sagittal plane passing through humerus. Collected FMG signals and the marker trajectories are fed into a Random Forest Regression algorithm. The results show an average squared correlation coefficient higher than 75%, on different hand gestures and locations, which proves the feasibility of using FMG signals to predict fine finger movements, in three predefined locations, for three different hand gesture.

Keywords: Medical Informatics, Image Processing/Pattern Recognition
Abstract: Glaucoma is an eye disease that causes irreversible loss of vision. Retinography is done manually by the ophthalmologist and is the cheapest, least invasive and most effective way to diagnose glaucoma. The ratio between the diameter of the outer part of the Optic Disc (OD) and the cup (internal part) called CDR (cup-to-disc ratio) is an important indicator of glaucoma presence in the patient. This paper proposes a semiautomatic approach that includes the segmentation of OD and cup regions. The proposed approach consists of four stages. The first stage consists of preprocessing the retinal image, in order to remove the blood vessels and their influence in the segmentation stage. In second stage we apply the Seeded Fuzzy C-means algorithm to segment the preprocessed image in order to find the regions of cup and OD. The third step involves the application of a post-processing so that non-segmented regions are filled. Finally, the last step calculates the value of the CDR associated with the retinal image. To verify the applicability of the proposed approach, we coonduced tests in two public images database: DRISHTI-GS and RIM-ONE r3. The results obtained illustrate the feasibility of applying the approach in order to effectively assist ophthalmologists in the segmentation of cup and OD, as well as the calculation of CDR value.

Keywords: Human Factors, Multimedia Systems, Machine Vision
Abstract: Facial wrinkle is one of the most prominent biological changes that accompanying the natural aging process. However, there are some external factors contributing to premature wrinkles development, such as sun exposure and smoking. Clinical studies have shown that heavy smoking causes premature wrinkles development. However, there is no computerised system that can automatically assess the facial wrinkles on the whole face. This study investigates the effect of smoking on facial wrinkling using a social habit face dataset and an automated computerised computer vision algorithm. The wrinkles pattern represented in the intensity of 0-255 was first extracted using a modified Hybrid Hessian Filter. The face was divided into ten predefined regions, where the wrinkles in each region was extracted. Then the statistical analysis was performed to analyse which region is effected mainly by smoking. The result showed that the density of wrinkles for smokers in two regions around the mouth was significantly higher than the non-smokers, at p-value of 0.05. Other regions are inconclusive due to lack of large-scale dataset. Finally, the wrinkle was visually compared between smoker and non-smoker faces by generating a generic 3D face model.

Keywords: Wearable Computing, Medical Informatics
Abstract: Monitoring periodic limb movements in sleep (PLMS) is important since it is correlated with people's quality of sleep and several other sleep disorders. The clinically approved method of examining PLMS is polysomnography (PSG) where the sleep of patients are examined in a laboratory with various sensors attached to their body. However, PSG is time-consuming and expensive for patients and the need for cost-effective and comfortable PLMS detection method has not been fulfilled. Accordingly, we propose a PLMS detection framework which utilizes a wearable motion-sensor-embedded band. In this work, we study the location to comfortably wear the device and accurately collect data on a foot. Further, to increase the accuracy of classifying PLMS, we propose the Motion Synchronized Windowing technique which segments the intervals where movements occur. Finally, we classify PLMS by using various machine learning algorithms typically used in the human activity recognition. Our proposed system achieves the accuracy of up to 96.92% in detecting PLMS. Therefore, our system is a cost-effective and convenient method of monitoring PLMS.

Keywords: Human Factors, Human-Machine Cooperation & Systems, Human-Computer Interaction
Abstract: Autonomous driving is on the horizon. Vehicles with partially automated driving capabilities are already in the market. Before the widespread adoption however, human factors issues regarding automated driving need to be addressed. One of the key issues is how much drivers trust in automated driving systems and how they calibrate their trust and reliance based on their experience. In this paper, we report the results of a survey conducted with Tesla drivers about their experiences with two advanced driver assistance systems, Autopilot and Summon. We found that drivers have high levels of trust in Autopilot and Summon. Trust decreased with age for Autopilot but not for Summon. Drivers who experienced unexpected behaviors from their vehicles reported lower levels of trust in Autopilot. Over time, trust in these systems increased regardless of experience. Additionally, trust was correlated with several attitudinal and behavioral factors such as frequency of use, self-rated knowledge about these systems, and ease of learning. These findings highlight the importance of trust in real world use of autonomous cars. Also, the results suggest that previous findings on trust in automation are applicable to real world cases as well.

Keywords: Human-Machine Cooperation & Systems
Abstract: This paper focuses on the control system design for a wearable power assist device which provides force/torque support for people who are doing physically demanding tasks. The device is actuated by the McKibben artificial muscle. The McKibben actuator is know to exhibit high nonlinearity between the supply pressure and the contractile length, and it is basically difficult to design a high performance controller. The present study proposes the use of the Minimal Controller Synthesis algorithm to design a high performance controller for the actuator. The user’s joint angular velocity, angular acceleration and the contact force exerted by the user to the frame are fed to the proposed controller to improve the response of the device to the human motion input while providing adequate assist force. Load lifting experiments have been conducted to evaluate the performance of the proposed control system.

Keywords: Human-Computer Interaction, Machine Learning, Computational Intelligence
Abstract: Electroencephalography (EEG) is the most frequently used technique to monitor functional activity of the brain. It has been widely employed in brain-computer interfaces based on the detection of P300 potentials. However, the P300 waves often contain physiological and non-physiological artifacts such as steady state visually evoked potential, power line or environment noise. The aim of this work is to eliminate undesirable periodic independent components from EEG, in order to enhance the P300 wave. The proposed method combines independent component analysis with a suitable selection of the most representative P300 components according to power features estimated from time measures using Parseval's theorem. The results show statistical differences (p<0.001) between the power spectral densities of raw and restored EEG, after Parseval-based component elimination. Additionally, the comparison of P300 latencies between raw and filtered EEG, showed statistical differences (p<0.001). Our findings suggest that this method can be helpful to eliminate undesirable components with significant narrow-band power, in order to preserve information required to enhance the P300 potential.

Keywords: Systems Safety and Security, Robotic Systems, Quality/Reliability Engineering
Abstract: With the rapid development of inspection techniques, more emphases should be placed on the improvement of the reliability, safety and intelligence of the robot system. In this paper, a framework for the patrol robot that automatically finishes complex task and motion planning in the indoor substation is proposed. To realize real-time response to the environmental changes, the proposed framework keeps an ongoing interaction with the environment as a Reactive System (RS). The RS employs the Transition System (TS) and Nondeterministic B"{u}chi Automaton (NBA) to create a discrete controller that bounds the acts of the patrol robot in the safe and reasonable specifications. What's more, the environment signals are treated as the trigger condition of task switching. If a new environment information is detected, our approach can automatically give a feasible plan. Then, the sensor-based mechanism of continuous controllers is guided by the discrete controller, which results in a hybrid system satisfying the high-level specification. The experiment within the LTLMoP toolkit verifies the proposed framework.

Keywords: Human Performance Modeling, Design Methods, Fuzzy Systems and their applications
Abstract: In this paper, we report on the design of a portable set of starting blocks for personal training to provide immediate feedback on the quality of sprinters' starting performance. The prototype set features two portable starting blocks with embedded sensors and a microcontroller for data collection and analysis. Testing was conducted with sprinters to validate and gauge the overall functionality of the prototype. Our preliminary results show that the force-time data produced using the prototype system do correlate with qualitative coaches' scores of sprinter's performance, and that the prototype system does show considerable promise for performance feedback.

Keywords: Medical Informatics, Machine Learning, Intelligent Internet Systems
Abstract: Medical search technologies are crucial to enable the user to rapidly and effectively discover useful information from massive medical and clinical data. Because of the complexity of medical terminology, traditional information search methods have not fully expressed the intention of the query request and explored the potential semantic knowledge in the document. In this paper, we propose a multi-analysis approach by considering the medical ontology as a semantic resource, which can excavate latent semantic information of a user’s query request. In addition, we also recognize topics of medical documents to express text contents for providing support for calculating the similarity between query keywords and documents. Our experiments on PubMed medical article collections show that the semantic-based multi-analysis approach is feasible and efficient compared with other traditional approaches in medical retrieval.

Keywords: Systems Safety and Security, Homeland Security, Communications
Abstract: In several critical military missions, more than one decision level are involved. These decision levels are often independent and distributed, and sensitive pieces of information making up the military mission must be kept hidden from one level to another even if all of the decision levels cooperate to accomplish the same task. Usually, a mission is negotiated through insecure networks such as the Internet using cryptographic protocols. In such protocols, few security properties have to be ensured. However, designing a secure cryptographic protocol that ensures several properties at once is a very challenging task. In this paper, we propose a new secure protocol for multipart military missions that involve two independent and distributed decision levels having different security levels. We show that it ensures the secrecy, authentication, and non-repudiation properties. In addition, we show that it resists against man-in-the-middle attacks.

Keywords: Human-Computer Interaction
Abstract: Skin resistance is one of the important indexes in psychological affective researches, and it can reflect the change of emotion by recording its changes. Generally, the skin resistance measurement method is connecting the electrode sensor to the two adjacent fingers of the object to record the resistance signal, and then amplifying, collecting and recording the signal by amplification circuit. However, the study found that in the actual measurement process, the skin resistance can produce non-emotional impact changes caused by the signal acquisition error and temperature fluctuation factors; thereby the actual measurement results can be interfered. This study improved the selection of sensor module and the amplification circuits to deal with this problem. As for the acquisition of signal, this study adopts the pet polyethylene glycol ester containing activated carbon as the electrode sensor material and selects the palm area as the signal collecting site; as for the amplification circuit, the differential amplification circuit which can restrain the drift effectively was chosen to realize the amplification signal function. The comparison experiment shows that the improved acquisition sensor module and differential amplification circuit can effectively improve the anti-interference ability of the skin resistance measuring device. Finally, this study proves that the experimental device can effectively measure the emotional changes of the object by using the experiment of fear and happy emotional stimuli.

Keywords: Human-Computer Interaction, Intelligence Interaction
Abstract: Myoelectric control with surface EMG signal has achieved great success in clinics, but only limited to the control of 2-Degrees-of-freedom prosthesis. With the appearance of multiple-channel and high-density EMG system and the advances of pattern recognition technology, it becomes possible to control a multi-degree smart prosthesis using EMG signals. However, it requires high performance EMG systems with high sampling frequency, which impedes the popularity of EMG-based applications. This study aims to explore a way to reduce the cost of EMG system by investigating the effect of sampling rate on gesture recognition accuracy. Two groups of experiments on inner-group and cross-group were designed to evaluate the classification accuracy at different EMG sampling frequency. In comparison with the sampling frequency at 1kHz, a lower sampling frequency at 400 Hz could achieve comparable accuracy, reduced by only 0.43% (KNN) and 0.83% (SVM) with the overall accuracy at 99.40% and 98.67%, respectively. It implies that appropriate reduction of the sampling frequency can be a good choice to balance the cost and performance of a multiple channel EMG system for feature-based hand gesture classification.

Keywords: Human-Machine Cooperation & Systems, Supervisory Control, Cooperative Systems and Control
Abstract: Levels of Autonomy (LoA) provide a method for describing authority granted to operators and autonomous system elements. Unfortunately, LoA does not provide the user interface designer a clear method to distinguish interface concepts which impose varying levels of operator workload or result in human or system performance changes. The current research suggests an alternate classification framework for vehicle control, referred to as the Level of Human Control Abstraction (LHCA). LHCA describes how an operator controls a system based on the control tasks performed and the level of detail of decisions made by the operator. The proposed framework consists of five levels: Direct Control, Augmented Control, Parametric Control, Goal-Oriented Control, and Mission-Capable Control. It is suggested that as the level of detail of control is reduced through progression from Direct Control to Mission-Capable Control, the level of human attention, and workload will be reduced.

Keywords: Interactive and Digital Media, Multimedia Systems, User Interface Design
Abstract: As the number of international tourist has been rapidly increasing recently, they have more opportunities to experience different cultures. With the upcoming Olympic game in Tokyo, Japan 2020, digital signage is expected to be utilized for an effective information presentation device for them. This study focuses on the information presentation with four-frame comic for foreign tourists to improve cross-cultural understanding. A subject experiment was conducted to compare four information presentation methods including the four-frame comic from the viewpoint of attractiveness and easy memorization. Participants from various countries watched Japanese food tradition information with four information presentation methods (four-frame comic, photograph, illustration and video) and evaluated their impressions. As a result, it was found that four-frame comic was easy to memorize although its attractiveness was different depending on the participants. However, as the experiment was conducted in a controlled laboratory, it is necessary to conduct a field study using a digital signage in the city to investigate the effective information method.

Keywords: Wearable Computing, Medical Informatics
Abstract: Heart failure (HF) is one of the most common causes of hospitalization for people over 65 years old, and over half of patients who diagnosed with severe HF conditions at first time cannot survive over 5 years. It is also noticed that rehospitalization rate of heart failure patients may increase to 50% in three months and the mortality rate from 33% to 50% within five years if HF patients are not treated with proper medication and physical therapies. Here we provide a classification system and an early warning mechanism for detecting HF disease based on integrating 6-minute walking test (6MWT), Internet of medical thing devices, and cloud computing technologies. This study performed 6MWTs for 50 HF patients accompanied by medical staffs for recording walkway distance, walking heart rate, and resting heart rate. All retrieved features and classified functional levels of heart organ of HF patients are trained as a target referencing dataset. According to the selected features and trained results, the clustered information representing various heart conditions is applied for detecting potential HF patients at earlier stages. In addition, the newly obtained self-exercise rehabilitation records from HF patients in a real-time manner will be compared to her/his previous 6MWT patterns. The compared differences are considered as important information for doctors to arrange medical treatment and adjusted physical therapy during the next follow-up visit in hospital.

Keywords: Human-Machine Cooperation & Systems, Systems Safety and Security
Abstract: This study investigated the effect of a secondary task when a takeover request (TOR) is received from an automated driving car, with a focus on nature of the secondary task (active or passive). Participants were asked to engage in one type of secondary task during automated driving, and we measured 1) forward gaze and 2) latency after the TOR to switch from automated to manual operation. Playing a game with a smartphone (active task) decreased driving-related performance in terms of shorter forward-gaze duration and longer delays in switching from TOR. In contrast, the performance in the other tasks (passively watching a video and conversing with another person) was little different from that in a condition with no secondary task. Compared to the tasks, not an active but a passive task would contribute to maintain the readiness for TOR.

Keywords: Human Performance Modeling, Brain-based Information Communications, Human Factors
Abstract: Long monitoring tasks without regular actions are becoming increasingly common from aircraft pilots to train conductors as these systems grow more automated. These task contexts are challenging for the human operator because they require inputs at irregular and highly interspaced moments even though these actions are often critical. It has been shown that such conditions lead to divided and distracted attentional states which in turn reduce the processing of external stimuli (e.g. alarms) and may lead to miss critical events. In this study we explored to which extent it is possible to predict an operator's behavioural performance in an Unmanned Aerial Vehicle (UAV) monitoring task using electroencephalographic (EEG) activity. More specifically we investigated the relevance of large-scale EEG connectivity for performance prediction by correlating relative coherence with reaction times (RT). We show that long-range EEG relative coherence, i.e. between occipital and frontal electrodes, is significantly correlated with RT and that different frequency bands exhibit opposite effects. More specifically we observed that coherence between occipital and frontal electrodes was: negatively correlated with RT at 6Hz (theta band), more coherence leading to better performance, and positively correlated with RT at 8Hz (lower alpha band), more coherence leading to worse performance. Our results suggest that EEG connectivity measures could be useful in predicting an operator's attentional state and her/his performances in ecological settings. Hence these features could potentially be used in a neuro-adaptive interface to improve operator-system interaction and safety in critical systems.

Keywords: Multimedia Systems
Abstract: Image annotation is an integral and important task for image retrieval. Automatic image annotation has been studied for quite some time now, but there is still scope for improvement considering the challenges associated with it. Existing systems focus on reducing the semantic gap between image and text using various heuristic, probabilistic or learning based approaches. Often, the automatic annotation tools segregate an image into discrete objects and try to annotate them. In doing so, they run the risk of missing out on important information conveyed by the image as a unit (concept). In this paper we propose a novel two-pronged probabilistic model based on a concept graph build out of such concepts which not only helps describe the objects in the image but also captures the essence of the image. To this end, we also employ an established community detection algorithm over the concept graph to identify the closest possible annotation for the image. A rigorous set of experiments on a standard dataset substantiates our proposed model's efficiency and efficacy.

Keywords: Assistive Technology, Technology Assessment, Human-Computer Interaction
Abstract: One of the challenges in children education is the inclusion of students with Down syndrome in regular schools. Some studies have discussed the advantages of using technological resources as mediation tools in literacy processes, as well as the impact of these resources in the distance education modality. However, an issue identified in the current state of the art is the lack of initiatives related to virtual learning environments (VLE) as a complementary resource in special education to improve literacy. To achieve this, it is important to analyze and evaluate criteria for choosing a VLE that considers the needs of students with Down syndrome. Considering this context, this paper presents an approach for evaluating VLEs considering specific requirements of students with Down syndrome. In addition, four virtual learning environments are analyzed in terms of adequacy considering the requirements for these students.

Keywords: Assistive Technology, Human Factors
Abstract: Personal mobility devices such as wheelchairs, bicycles, and compact cars are used in daily life and to runs on sidewalks. However, there are several factors that may lead to discomfort rides, such as steps, slopes, and crowded sidewalks for a passenger.

This paper proposes a system that detects the factors using smartphone attached to the personal mobility device and generates a discomfort-ride map including the environment and human factors and their rating on sidewalks.

In the experiment, steps (static danger factor) and the dynamic moving obstacles like human, bicycle, and car (dynamic danger factors) were estimated with attached smartphone's acceleration sensor and camera. After the process of collecting these data, verification for generating the hazard map system based on these data. Moreover, the versatility of using the proposed hazard map system for different personal mobility devices was tested with the electric wheelchair and the bicycle.

Keywords: Human Performance Modeling, Human-Machine Interface Web
Abstract: Humans modify their movement characteristics according to the requirement of the movement accuracy. The relations between the required accuracy and muscle activities were previously determined by varying the size of the targets to be reached in isotonic contraction tasks. However, in isometric contraction tasks, such relations have not been studied yet. In this study, we examined whether there was a difference in the movement characteristics depending on the sizes of the targets being introduced. We observed that the distribution of the forces at the end of the movement varied with the target sizes, similar to results of previous studies based on isotonic contractions. Furthermore, we noted a trade-off relation between the required accuracy and co-contraction of the muscles. When we examined the muscle synergies, we observed that for some subjects, the number of synergies increased with the increase in target size. This result suggested that the strategy of motor control might be modified depending on the requirement of accuracy of the isometric reaching task considered herein.

Keywords: Systems Safety and Security, Technology Assessment
Abstract: Threats to information security can have great impact on business finances and company’s reputation. Traditional methodologies for evaluating the maturity of data centers investigate security parameters to determine the compliance of data centers and international security norms. This paper proposes two innovative evaluation procedures to capture other security perspectives on data center environments: (1) weighted analysis - it weights higher security controls simultaneously present in a higher number of norms; (2) it is sensitive to the importance level that the organization assigns to each security control. Through the proposed methodology, security engineers can identify security issues, characterize the security maturity, and suggest new policies improve security configurations of data centers. This paper also includes a case study to evaluate the benefits of the methodology in real-world scenarios. Results demonstrated that the proposed methodology evaluates higher the security elements more relevant for the company, where as traditional approaches consider all security aspects to be equally important.

Keywords: Resilience Engineering, Robotic Systems
Abstract: This paper presents a new under-actuated resilient robot that has the three recovery processes available, as we proposed elsewhere. The new feature with the proposed resilient robot is such that all the recovery strategies can be accomplished in a 2D plane instead of a 3D space, thus reducing the complexity of the recovery process. The robot also has the ability of switching between a fully-actuated robot and an under-actuated robot with the help of an electromagnetic clutch.

Keywords: Human-Machine Cooperation & Systems, Human-Computer Interaction, Self-Organization
Abstract: The ongoing modernization of today’s workplaces within the framework of industry 4.0 is leading to radical new developments and forcing fundamental changes to the way companies and factories are established. The purpose of this paper is to develop and improve a concept that organizes the workplace on a basic level in order to meet the upcoming challenge of accounting for robots as key players in it. There are several organizational structures that include the traditional hierarchical structures as well as the modern agile management models that are rising in the world of industry 4.0. Within it, the usage of robots is increasing due to the vast and multiple functions each robot is able to perform. This implies automation, but it also implies that different forms of collaboration with humans are becoming necessary as factories are tending to produce customized products. Individualized products require different methods and different skills which span different sets of abilities of humans and robots. How does this increase of robots’ usage affect the applied organization structures and flows of the decision-making processes? What are necessary changes that need to be considered to maximize the efficiency and effectiveness of a workplace with robots that already existing structures do not compensate for? This paper highlights the existing gap and addresses the required changes in the organization models. Following that is an evaluation and outlook on that validates the legitimacy of the approach.

Keywords: Augmented Cognition, Human-Computer Interaction, User Interface Design
Abstract: As the ubiquity of computers, computer-mediated communications (CMC) has evolved to satisfy one of humanity’s basic needs - communication today. Text-based message exchanging has established itself as the most popular CMC medium in our lives than other modes of communication. Compared to face-to-face communication, CMC is not restricted in terms of time and place However, text-based communications lack much of the richness of contextual information. It has been argued that nonverbal cues such as emotions are effective in helping users understand the meaning and nature of the message. The aim of this paper is to use empirical evidence to gain insight in how different CMC interaction methods influence the sensing of emotions and how this embed breaks down emotion barriers between CMC users. We also report how emotion can affect different user groups in CMC.

Keywords: Human Performance Modeling, Information Visualization, Fuzzy Systems and their applications
Abstract: Brain-state drifts could significantly impact on the performance of machine-learning algorithms in brain computer interface (BCI). However, less is understood with regard to how brain transition states influence a model and how it can be represented for a system. Herein we are interested in the hidden information of brain state-drift occurring in both simulated and real-world human-system interaction. This research introduced the Riemann metric to categorize EEG data, and visualized the clustering result so that the distribution of the data can be observable. Moreover, to defeat subjective uncertainty of electroencephalography (EEG) signals, fuzzy theory was employed. The clustering results in 2-D space and the classification results are also shown in this paper, respectively.In this study, we built a fuzzy rule-based brain-state-drift detector to observe the brain state and imported data from different subjects to testify the performance. The result of the detection is acceptable and shown in this paper. In the future, we expect that brain-state drifting can be connected with human behaviors via the proposed fuzzy rule-based classification. We also will develop a new structure for a fuzzy rule-based brain-state-drift detector to improve the detection accuracy.

Keywords: Information Systems for Design/Marketing, Human Factors
Abstract: The long-tail phenomenon tells us that there are many items in the tail. However, not all tail items are the same. Each item acquires different kinds of users. Some items are loved by the general public, while some items are consumed by eccentric fans. In this paper, we propose a novel metric, item eccentricity, to incorporate this difference between consumers of the items. Eccentric items are defined as items that are consumed by eccentric users. We used this metric to analyze two real-world datasets of music and movies and observed the characteristics of items in terms of eccentricity. The results showed that our defined eccentricity of an item does not change much over time, and classified eccentric and noneccentric items present significantly distinct characteristics. The proposed metric effectively separates the eccentric and noneccentric items mixed in the tail, which could not be done with the previous measures, which only consider the popularity of items.

Keywords: Virtual and Augmented Reality Systems, Machine Vision
Abstract: This paper proposes a new camouflage system that uses RGB-D cameras, for acquiring point cloud of the background scene, and tracking observers’ eyes. This system enables a user to conceal an object located behind a display that surrounded by 3D objects. If we considered here the tracked point of observer’s eyes is a light source, the system will work on estimating shadow shape of the display device that falls on the objects in the background. The system uses the 3d observer’s eyes and the locations of display corners to predict their shadow points which have nearest neighbors in the constructed point cloud of background scene.

Keywords: Decision Support Systems, Knowledge Acquisition in Intelligent, Machine Learning
Abstract: Sentiment analysis is able to automatically extract valuable customer sentiment information from large amount of unstructured text data to support decision makings in manufacturing applications such as product design and demand planning. One of the key issues of sentiment analysis for text data is extremely high data dimensionality which can be effectively solved by feature selection. The existing feature selection techniques compute feature scores either solely based on training data statistics, or by modifying a specific feature metric formula to include test data information which can not be generalized to other types of feature metrics. In this paper, we propose an Adaptive Two-Stage (ATWS) feature selection approach, which generates base feature scores from training dataset and then weights them based on individual test sample so that the feature importance evaluation is adapted to the characteristic of test data as well. A heuristic tri-band parameter setting strategy is also introduced to reduce the number of hyper-parameters required to set the weight coefficients. The proposed method is applicable to arbitrary type of feature metrics and sentiment classifiers. The experiment results show that our approach can consistently outperform other methods,especially for the setting of small number of selected features.

Keywords: Decision Support Systems, Technology Assessment, Infrastructure Systems & Services
Abstract: Determining site suitability for utility-scale solar PV power plants requires complex decisions. Basing such decisions on extensive information, especially from the geographical information system (GIS), offers significant advantages such as improved project performance, minimized power loss, and reduced environmental impacts. The primary aim of this research is to evaluate the ideal location for utility-scale solar PV projects using the GIS combined with a Fuzzy Analytic Hierarchy Process (AHP) in the country of Saudi Arabia. Various economic and technical factors are considered in the proposed model and are ranked using a fuzzy AHP approach. The best selection for solar PV is a tradeoff between maximum power achievement and minimal project cost. An analysis of land suitability is computed to classify the suitability area into three different categories: “high,” “moderate”, and “low”. The results obtained from the analysis show that 15% and 8.2% of the study areas show high and moderate suitability levels, respectively. By considering only 10% of the highly suitable land, the potential power generated per year could reach 8,330,807 GWh, which is 28 times greater than the current energy sales in Saudi Arabia, which is around 294,612 GWh/year.

Keywords: Infrastructure Systems & Services
Abstract: The perfect relationship between deployment costs and systems availability is one of the primary goals of companies that wish to provide some computer environment or service through the Internet. The question that everyone wants to know the answer is: How much may I save and still improve the availability of my system avoiding financial losses with an SLA contract breach? This paper attempts to respond to this question by combining some techniques used at dependability evaluation field, such like hierarchical models, sensitive analysis techniques, and analysis costs. The models shown in this paper are artifacts and scenarios for a data synchronization server hosted at a private cloud computing platform based on Eucalyptus. Each scenario presented here was generated to study the impact of redundant techniques in the system availability and deployment cost. By analyzing each architecture separately and comparing them, we can indicate the one that has the best cost-benefit relationship and attends the providers, as well as the client's needs.

Keywords: Decision Support Systems
Abstract: With the rapid development of big data analytics in online marketing, real-time bidding (RTB) has emerged as a promising business model in recent years, and now becomes one of the major online advertising channels. Based on analysis of Web Cookies, RTB platforms are able to precisely identify the features and preferences of target audiences visiting publishers’ websites, and forward the generated ad impressions to competing advertisers who submit bids for their best-matched audience in real-time ad auctions. In RTB markets, reserve price serves as an important tuner to exclude advertisers with low estimated values, and hence can guarantee a desirable result for the publisher from ad impression auctions. In this paper, we strive to study publishers’ strategy on the reserve price, and probe the impact of reserve price on their revenues. We first analyze the ad impression auction under a direct auction mechanism. We then introduce the reserve price and study its impact on publishers’ revenues under an indirect auction mechanism, and our research findings indicate that a rational positive reserve price will always improve publishers’ revenues even if it is not optimal. Also, the optimal reserve price is figured out based on the advertisers’ bid distributions for publishers’ revenue maximization. Finally, experiments using empirical log data from real-world RTB markets are designed to validate our model and analysis, and the results provide strong support to our theoretical analysis. The experimental results also indicate that although the number of bids does not impose any influence on the optimal reserve price, it has significant impacts on publishers’ revenues.

Keywords: Decision Support Systems, Fuzzy Systems and their applications, Computational Life Science
Abstract: The commonly used preference elicitation method in decision making is the one using pairwise comparison between alternatives. In this kind of decision making scenario, an essential issue requiring attention is that of consistency, particularly in decision problems with numerous alternatives. Consistency is usually linked to the transitivity concept, which is modeled in several diverse ways. Given the importance of avoiding conflicting opinions in decision making, in this study, we propose an approach to improve the consistency when reciprocal preference relations are used. On one hand, consistency is modeled in terms of the multiplicative transitivity property. On the other hand, information granularity is used to introduce and develop the concept of interval reciprocal preference relations in which the entries are constructed as intervals in place of single numeric values. This provides the necessary flexibility to improve the consistency. To illustrate and test the performance of the approach that is proposed here, an example is given.

Keywords: Decision Support Systems, Expert and Knowledge-based Systems
Abstract: In multiple attribute decision analysis (MADA) problems, one often needs to deal with assessment information with uncertainty. The evidential reasoning approach is one of the most effective methods to deal with such MADA problems. As a kernel of the evidential reasoning approach, an original evidential reasoning (ER) algorithm was firstly proposed by Yang et al, and later they modified the ER algorithm in order to satisfy the proposed four synthesis axioms. However, up to the present, the essential difference of the two ER algorithms is still unclear. In this paper, we analyze the ER algorithms in the Dempster-Shafer theory framework and prove that the original ER algorithm follows the reliability discounting and combination scheme, whereas the modified one follows the importance discounting and combination scheme. Based on these new findings, an extended ER algorithm is proposed to take into account both the reliability and importance of different attributes, which provides a more general attribute aggregation scheme for MADA with uncertainty. A motorcycle performance assessment problem is examined to illustrate the proposed algorithm.

Keywords: Decision Support Systems, Enterprise Information Systems, Communications
Abstract: Advances in technology and the need to meet many interdependent competing requirements have led to complex information intensive systems that can be best managed by integrating multi-discipline, multi-attribute models for better informed decision-making. Attempts to bridge the gap between systems engineering and project management have been sought through project management methods and through imposing practices from one discipline onto another. It is proposed that a more rigorous approach to bridging this gap be investigated to better enable the optimization of objectives, collaboration, and cooperation amongst multiple disciplines. The disciplines of interest in this study are plant modeling, systems engineering, and program management. In bridging the gap, both leveraging models from the different disciplines and adopting six sigma tools and visualization techniques are investigated. Common variables and outcome-based attributes provide a mechanism to integrate multi-discipline models. Options to bring together models from each discipline include multi-disciplinary system design optimization (MSDO). To demonstrate the feasibility of integrating multi-discipline attributes on a common platform, a case study on design of a notional future marine Integrated Power System (IPS) is investigated using a modified Multi-Attribute Tradespace Exploration (MATE) – Capability model. This case study highlights the need to integrate other multi-discipline models to help validate specific system attributes of interest.

Keywords: Enterprise Information Systems, Decision Support Systems, Consumer/Industrial Applications
Abstract: Key Performance Indicators (KPIs) are used to inspect the performance and progress of businesses. This study introduces a new, integrated approach to manage KPIs in the context of decentralized information efficiently and to address the visual and managerial gaps existing in companies. The proposed Business Indicator Management (BIM) system is essential for any businesses to meet their needs in terms of information availability and agility as well as time efficiency and quality of the decision-making task. Thanks to BIM, executives are now able to obtain real-time information and analysis of the actual situation of their businesses, thus increasing their productivity. Today, no companies have yet this type of managing KPIs. Based on a detailed case study with a big-scale corporation, we thoroughly assess the effectiveness of BIM according to the system usability, data agility and decision making efficiency.

Keywords: Conflict Resolution
Abstract: A development planning approach combining game theory and network model is proposed to address the strategy selection and evolution for weapons system-of-systems (WSoS) characterized by an iterative and competitive development process between countries. More specifically, the development planning framework, including game player, strategy definition, and constraints (e.g., time and money), is first described, in which combat network is constructed to present the structure and evolution of WSoS. Next, the selection process of development planning strategy is studied based on damage accumulation and mitigation related to WSoS confrontation. Then, a competitive coevolution algorithm (CEA), reflecting that WSoS evolves along with the strategy selection change, is designed to find the optimal development strategy. Last, an illustrative example is used to demonstrate the feasibility and validity of the proposed approach.

Keywords: Decision Support Systems, Distributed Intelligent Systems, Quality/Reliability Engineering
Abstract: Internet of things, a trend of the following years, makes it possible to develop new applications and services as well as creates a huge amount of data to be processed. In order to support this new paradigm, an extension of cloud computing, named Fog Computing, has been developed. Fog computing improves the cloud security, availability and performance by pro- viding a distributed and powerful communication environment with short delay. Therefore, this new paradigm complements the cloud computing. However, the fog faces several issues such as quality of service (QoS) and multi-tenancy optimisation and load balancing. This paper proposes the algorithm called Multi-tenant Load Distribution Algorithm for Fog Environments (MtLDF) to optimise the load balancing in Fogs environments considering specific multi-tenancy requirements (delay and priority). Finally, we present case studies to show the applicability of the proposed algorithm in comparison to a Delay-Driven Load Distribution (DDLD) strategy.

Keywords: Image Processing/Pattern Recognition, Information Visualization, Human Factors
Abstract: In this paper, we propose a computational strategy to enhance the performance of Image Quality Metrics (IQM) by using content specific features of an image. We do this by creating Visual Error Importance (VEI) map that is applied to the error maps computed by the IQM. A global optimization can be used to compute the VEI map that is optimal for any given IQM. We demonstrate this concept by categorizing the image content into three classes, generating and applying VEI to different IQM’s and showing performance improvement in all of the cases. The performance evaluation was conducted on CSIQ dataset.

Keywords: Machine Learning, Machine Vision, Image Processing/Pattern Recognition
Abstract: Video summarization plays an important role in providing a compact representation of large volumes of video sequences through the search for the most informative or representative portions of their content. In this work, we propose and analyze a novel video summarization method based on texture and color information to describe the video frames in order to produce an effective visual abstract of the video sequence. Experiments conducted on a data set containing distinct genres demonstrate that the proposed method is capable of generating competitive video summaries when compared to other approaches available in the literature.

Keywords: Image Processing/Pattern Recognition, Machine Vision, Machine Learning
Abstract: Despite its associated challenges, the development of mechanisms for storing, indexing, transmitting and visualizing multimedia content is crucial in order to efficiently deal with the large amount of data generated by several different sources. Digital video technology has advanced rapidly, such that temporal video segmentation methods for automatically detecting transitions in video sequences play an important role in the content analysis tasks. In this work, we propose and evaluate a video shot boundary detection approach based on the Weber local descriptor. Experiments conducted on different datasets demonstrate the effectiveness of our method, whose results are compared against other approaches of the literature.

Keywords: Machine Vision, Machine Learning, Neural Networks and their Applications
Abstract: This work focuses on cost reduction methods, applied on forest species recognition systems as a case-study. Current state-of-the-art shows that the accuracy of these systems, generally employing texture recognition approaches, have increased considerably in the past years. However, the cost in time to perform the recognition of input samples has also increased proportionally. By taking into account previous research that demonstrated that cost reduction at classification level can provide much faster systems, in this work we focus on proposing metrics to measure the impact of cost reduction at another important module of image recognition system, i.e the feature extraction stage, and on how to measure cost reduction at global level, i.e. combining cost reduction at both feature extraction and classification. The evaluation of the proposed metrics on a forest species dataset demonstrated that, with global cost reduction, not only the cost of the system can be reduced to less than 1/20, but also the recognition rates can be improved.

Keywords: Image Processing/Pattern Recognition, Homeland Security, Machine Vision
Abstract: Abstract—Target re-identification via cross-camera is a difficult problem in the field of target discovery and tracking. Traditional solutions depending on the characteristics of a target’s appearance have low reliability and can easily lead to low matching rate because they use simple metric functions. This work proposes a more reliable measurement: correlative degree of a target’s features among different camera views to do target re-identification and uses it to measure the histograms' similarity of targets. In order to obtain more discriminative features, we need to extract their appearance and space features. We use multi-layer histograms to describe them. In order to compute more accurate correlation degree, we propose to use Gaussian pyramid as alternating distance to define high-dimensional diffusion distance. Finally, we assign different weights to feature vectors so as to establish the correlative degree function based on diffusion distance. Experiments of target re-identification for different cameras show that the proposed method can achieve much better results than some known existing methods.

Keywords: Image Processing/Pattern Recognition, Machine Vision
Abstract: In this paper, a temporally iterative Gaussian Mixture Model (GMM) of Dynamic Texture (DT) for target detection using a moving PTZ camera, is proposed. Camera movement in a PTZ sensor causes motion-based target detection techniques to fail for the periods affected by the scene change. This is because the whole scene is considered a representation of the target motion. When the camera is in motion, conventional background models remain invalid until the time that the model has adapted and updated its parameters to the newly perceived scene. The proposed model is based on an iterative modeling of spatio-temporal patches that represent the visual scene using GMM-of-DT. During the initial iteration of the proposed GMM-of-DT model, the input video is temporally segmented into clips in a manner that separates global from local motion. Further, parameters of the GMM-of-DT model are estimated for each temporal segment and in subsequent iterations updated adaptively to generate the final foreground mask. The proposed technique is tested and verified on video scenes from public datasets.

Keywords: Image Processing/Pattern Recognition, Expert and Knowledge-based Systems, Multimedia Computation
Abstract: This paper proposes a novel digital image watermarking method that allows to intelligently embed a gray-scale watermark image into a color host image on the wavelet domain. By decomposing a gray-scale image to binary images in digit ordering from LSB to MSB, binary bits are then encoded to optimal wavelet coefficient blocks using a quantization technique in which a wavelet coefficient difference is quantized to either of two pre-identified thresholds for corresponding 0-bit or 1-bit embedment. To boost visual quality of the host image, an embedding rule is improved by equal spreading coefficient adjustment on two middle-frequency sub-bands instead of only one as the existing approaches. Additionally, 2D Otsu algorithm, more proficient than 1D Otsu algorithm for segmentation in a noise condition, is modified to flexibly calculate an optimal threshold for high-rate watermark extraction. Experimental results demonstrate the proposed watermarking model reaches a remarkable imperceptibility as well as a high robustness against common digital image transformations.

Keywords: Image Processing/Pattern Recognition, Machine Vision, Machine Learning
Abstract: The Earth observation satellites have been monitoring the earth's surface for a long time, and the images taken by the satellites contain large amounts of valuable data. However, it is extremely hard work to manually analyze such huge data. Thus, a method of automatic object detection is needed for satellite images to facilitate efficient data analyses. This paper describes a new image feature extended from higher-order local autocorrelation to the object detection of multispectral satellite images. The feature has been extended to extract spectral inter-relationships in addition to spatial relationships to fully exploit multispectral information. The results of experiments with object detection tasks conducted to evaluate the effectiveness of the proposed feature extension indicate that the feature realized a higher performance compared to existing methods.

Keywords: Image Processing/Pattern Recognition, Machine Vision
Abstract: To overcome visual object tracking challenges, various feature-based object trackers use feature combination. Each feature component is developed to overcome certain tracking challenges, but the interaction between the components may cause tracking errors. We propose a tracking solution based on human vision principles to reduce combination errors by adaptively fusing each feature using its previous performance. An adaptive fusion technique is developed to determine feature quality using feature likelihood map variance ratios. The proposed method is completely modular, while reducing the risk of tracker failure. Experimental results on the Visual Object Tracking database show the proposed tracker's robustness and its advantage over state-of-the-art trackers.

Keywords: Image Processing/Pattern Recognition, Multimedia Computation, Multimedia Systems
Abstract: Feature ranking from video-wide temporal evolution brings reliable information for complex action recognition. However, a video may contain similar features in the sequence of frames which deliver unnecessary information to the ranking function. This paper proposes a method to improve the rank-pooling strategy which captures the optimized latent structure of the video sequence data. The optimization is followed by removing the redundant features from the sequence data. The cosine and correlation distance metrics are employed to detect the identical features and extract the most efficient information from the video frames. Then, the ranked features are generated from the optimized and clean sequence data. The proposed improvement is easy to implement, fast to compute and effective in recognizing complex actions. As a result, the proposed approach reaches remarkable action recognition performance on benchmark datasets, namely Hollywood2, URADL, and HMDB51. The results are further compared with state-of-the-art techniques in the experiment section to confirm the effectiveness of the improved rank pooling framework.

Keywords: Machine Learning
Abstract: Real-world datasets are often imbalanced, with an important class having many fewer examples than other classes. In medical data, normal examples typically greatly outnumber disease examples. A classifier learned from imbalanced data, will tend to be very good at the predicting examples in the larger (normal) class, yet the smaller (disease) class is typically of more interest. Imbalance is dealt with at the feature vector level (create synthetic feature vectors or discard some examples from the larger class) or by assigning differential costs to errors. Here, we introduce a novel method for over-sampling minority class examples at the image level, rather than the feature vector level. Our method was applied to the problem of Glioblastoma patient survival group prediction. Synthetic minority class examples were created by adding Gaussian noise to original medical images from the minority class. Uniform local binary patterns (LBP) histogram features were then extracted from the original and synthetic image examples with a random forests classifier. Experimental results show the new method (Image SMOTE) increased minority class predictive accuracy and also the AUC (area under the receiver operating characteristic curve), compared to using the imbalanced dataset directly or to creating synthetic feature vectors.

Keywords: Assistive Technology, Human-Computer Interaction, Augmented Cognition
Abstract: This paper investigates visual attention control using the presentation of directional flow stimulus to peripheral vision. Peripheral vision is known to have a superior motion-perception capability. Since central vision is usually used for a primary visual task, it would be quite useful if we could control one's attention by providing assistive information through peripheral motion cues without interfering with the primary task. To evaluate the effectiveness of the proposed method, we conducted experiments on rapid target recognition and visual search tasks under peripheral stimulation conditions. As a result, in the target recognition task, we confirmed that the position with the highest recognition score corresponds to the direction of the presented flow stimuli. In a visual search task, response time decreases when the target position and flow direction match. Furthermore, such matching allows the subjects to more quickly learn how to use the presented information in their search task. Subjective evaluation by questionnaire also demonstrates the intuitiveness and helpfulness of the proposed method. These results support the effectiveness of attention control and visual search assistance using the presentation of directional flow stimuli to peripheral vision.

Keywords: Assistive Technology, Human Performance Modeling, Machine Learning
Abstract: Abstract—Because of the worldwide aging population, more and more elders suffer from dementia. Nowadays, it is inconvenient and time-consuming for doctors to diagnose whether elders who live independently have dementia because lots of diagnostic questions on a checklist must be asked first, and part of them even require a long-term observation. In order to help doctors and make this diagnostic process easier, we proposed a supporting system that can quickly screen the elders and estimate the likelihood of them having dementia based on a behavioral test in 2 to 4 hours. During the behavioral test, the elders only need to perform some activities selected from so-called Instrumental Activities of Daily Living (IADL) in a smart home environment, and a machine learning algorithm is adopted to carry out the classification based on our proposed features extracted from motion sensors deployed in the smart home environment. Our system supports the classification of two classes, Dementia and Non-Dementia, and its average precision and recall are both up to 98.3%. Besides, the value of Area Under the ROC Curve (AUC) is 0.851.

Keywords—Dementia; quickly screen; smart home; motion sensors; machine learning

Keywords: Assistive Technology, Human-Computer Interaction
Abstract: Continuous EMG control of human-machine interfaces (HMIs) enables more direct and flexible control of output movements than discrete classification algorithms. However, EMG is a non-stationary signal and can add noise to continuous EMG control output. We studied the effect of an output speed threshold method to stabilize the movement prediction of a 2-DOF musculoskeletal model-based continuous EMG controller during a real-time virtual task. In each of several trials, three able-bodied subjects were instructed to move and align the palm and finger segments of a virtual hand with four different target postures on a computer screen. Three different thresholds on the model’s predicted angular speed were applied in a randomized order across trials: no threshold, medium threshold (15 °/sec), and high threshold (30 °/sec); the virtual hand did not move if the predicted angular speed at the next timepoint did not exceed the threshold. We recorded completion time, overshoot, jerk, and number of failed trials to quantify task performance. In a separate block of trials, subjects reported their threshold preference following multiple pairwise comparisons. The number of overshoots decreased and jerk magnitude increased with higher threshold levels. The average completion time was lowest with the medium threshold for 2 subjects. All 3 subjects had lower failed trials with either the medium or high threshold. The subject preference score showed an inverse trend with the number of failed trials. In summary, the presented threshold method was successful in reducing overshoot and trial failures, and a threshold was preferred by all subjects over no threshold. Thus, an output speed threshold may improve the functional performance and user satisfaction of continuous EMG control for HMIs, such as powered upper limb prostheses.

Keywords: Assistive Technology, Human-Computer Interaction
Abstract: Visually impaired people are neglected from many modern communication and interaction procedures. Assistive technologies such as text-to-speech and braille displays are the most commonly used means of connecting such visually impaired people with mobile phones and other smart devices. Both these solutions face usability issues, thus this study focused on developing a user friendly wearable solution called the `BrailleBand' with haptic technology while preserving affordability. The `BrailleBand' enables passive reading using the Braille language. Connectivity between the BrailleBand and the smart device (phone) is established using Bluetooth protocol. It consists of six nodes in three bands worn on the arm to map the braille alphabet, which are actuated to give the sense of touch corresponding to the characters. Three mobile applications were developed for training the visually impaired and to integrate existing smart mobile applications such as navigation and short message service (SMS) with the device BrailleBand. The adaptability, usability and efficiency of reading was tested on a sample of blind users which reflected progressive results. Even though, the reading accuracy depends on the time duration between the characters (character gap) an average Character Transfer Rate of 0.4375 characters per second can be achieved with a character gap of 1000ms.

Keywords: Assistive Technology, Human-Machine Cooperation & Systems
Abstract: Force Myography (FMG) is a method of tracking functional motor activity using volumetric changes associated with muscle function. With comparable accuracy and multiple advantages over traditional methods of functional motor activity tracking, FMG has shown a promising potential in terms of applications in human-machine interfaces, tele-operation and healthcare devices. This paper provides a study that explores the effect of the spatial coverage and placement of the Force Myography (FMG) measurements on the accuracy and predictability of the machine learning models of isometric hand force. Five participants were recruited in this study and were asked to exert isometric force along three perpendicular axes while wearing custom built FMG devices. During the tests, the isometric force was measured using a 6 degree-of-freedom (DOF) load cell whereas the FMG signals were recorded using a total number of 60 FSRs, which were embedded into four bands worn on the arm. General Regression Neural Network (GRNN) model was employed in this study for predicting the hand force in three axes from the recorded FMG signals. The regression model was trained using all possible band combinations to find the optimal placement for the FMG measurements. The results showed that the accuracy significantly improved when increasing the spatial coverage from 1 FMG band to 2 or 3 bands for all axes. While the accuracy slightly improved when the 4 bands used instead of 3. Specifically, the average R2 across all subjects and axes are 0.68 ± 0.12, 0.84 ± 0.04, 0.91 ± 0.02 and 0.95 ± 0.01 using single, double, triple and four bands combination, respectively, in 5-fold cross-validation evaluation. The knowledge generated from this work aims serve as a guide towards the development of portable FMG based technology for widespread deployment in the general population.

Keywords: Assistive Technology, Interactive and Digital Media, Image Processing/Pattern Recognition
Abstract: Because visually impaired persons are not able to confirm the appearance of their own face, they are afraid of and uneasy about makeup. We have been developing a system that assists makeup application through verbal feedback according to the appearance of the user's face. The system encourages social communication by helping the user feel confident. In this paper, we introduce a new method of using a dedicated camera device and an image processing algorithm to quantify lip makeup. We designed the camera device to capture face images under different illumination types; white light and green light. In the image processing, we extract the lip area from a segmentation that uses the difference in saturation between two lighting conditions. We also developed a symmetry histogram-based geometrical feature of lip shape to estimate the symmetrical characteristics. The experimental results show that the proposed approach yields results close to a human's subjective evaluation.

Keywords: Assistive Technology, Machine Vision, Neural Networks and their Applications
Abstract: In this paper we are presenting a novel approach for navigational path detection problem for the visually impaired using image data from RGB cameras. We are employing a deep learning model based on state-of-the-art fully convolution neural networks that can accurately semantically segment any navigational areas on pixel-wise level in different scenes without any prior assumptions about the environment of the scene such as textures or specific appearance cues. The proposed approach have been evaluated on two different publicly available dataset and have achieved a pixel accuracy of 91% over the testing images dataset. We further evaluated the performance of the proposed approach against other commonly used approach for the problem of predicting navigational areas in input RGB images, and we have outperformed it with more than 14%, 11% and 10% on the mean intersection over union, mean accuracy and pixel accuracy evaluation metrics respectively.

Keywords: Assistive Technology, Optimization
Abstract: Brain-computer interfaces (BCIs) can provide an alternative means of communication for individuals with severe neuromuscular limitations. The P300-based BCI speller relies on eliciting and detecting transient event-related potentials (ERPs) in electroencephalography (EEG) data, in response to a user attending to rarely occurring target stimuli amongst a series of non-target stimuli. However, in most P300 speller implementations, the stimuli to be presented are randomly selected from a limited set of options and stimulus selection and presentation are not optimized based on previous user data. In this work, we propose a data-driven method for stimulus selection based on the expected discrimination gain metric. The data-driven approach selects stimuli based on previously observed stimulus responses, with the aim of choosing a set of stimuli that will provide the most information about the user's intended target character. Our approach incorporates knowledge of physiological and system constraints imposed due to real-time BCI implementation. Simulations were performed to compare our stimulus selection approach to the row-column paradigm, the conventional stimulus selection method for P300 spellers. Results from the simulations demonstrated that our adaptive stimulus selection approach has the potential to significantly improve performance from the conventional method: up to 34% improvement in accuracy and 43% reduction in the mean number of stimulus presentations required to spell a character in a 72-character grid. In addition, our greedy approach to stimulus selection provides the flexibility to accommodate design constraints.

Keywords: Assistive Technology, Wearable Computing, Human Factors
Abstract: The elderly sometimes fall due to the tripping caused by decreased dorsal flexion during swing phase. A wearable assist device, which increased dorsal flexion to reduce the risk of tripping, was proposed in this study. This device assists dorsal flexion during swing phase by transferring tension force using strings from upper body to foot by connecting them. To achieve efficient assist, string paths were optimized to maximize assist torque at correct timing. In this study, two string path patterns were tested. As a result of walking experiment, the wearable assist device we developed successfully increased both dorsal flexion and minimum foot clearance during swing phase.

Keywords: Brain-based Information Communications, Human-Computer Interaction, Assistive Technology
Abstract: Error-related electroencephalographic (EEG) potentials (ErrPs) have been explored to improve the reliability of modern Brain-Computer Interfaces (BCIs), thanks to the information they carry about user awareness of erroneous responses. ErrPs detection on a single-trial basis has been successfully demonstrated, and proved to effectively enhance human-computer interaction and BCI performance. Previous studies tested ErrPs elicited by providing either visual or tactile feedback, showing similar results for all feedback modalities. In the present work, we tested: 1) whether the addition of tactile feedback can improve the detection of ErrP, when used in combination and not alternatively to visual feedback; 2) whether a mismatch between the two different sensory channels can enhance ErrP detection. Results on a study carried out on 12 healthy subjects show that the addition of tactile stimuli significantly affects single-trial ErrP recognition (AUC increment of 4.3%) without significant difference in case of concordant or discordant visual and tactile stimuli

Keywords: Human Factors, Assistive Technology, Human-Computer Interaction
Abstract: In this paper, we experimentally examine the relationship between visual cognition difficulty and target-tracking eye movements, which recorded during moving target cognition. Generally, such eye movements are observed when humans perceive a moving object and they vary widely due to many factors, such as target shape, backgrounds, illumination conditions, and so on. Several systems have been proposed for estimating human cognition based on gaze movements. However, since most of them employ simple thresholding techniques to classify the states of cognition, their classification performance remain insufficient. This research clarifies the relationship between multiple visual conditions and target-tracking eye movements to enhance the classification performance. We found that we can address a variety of target and background factors from the perspective of visual cognition difficulty for the targets. Observed gaze movement properties and the difficulty of target visual cognition have a linear relationship, suggesting the possibility of more precise estimation of human’s target cognition based on them.

Keywords: Robotic Systems, Heuristic Algorithms, Decision Support Systems
Abstract: It is necessary for a mobile robot to be able to efficiently plan a path from its starting, or current location to a desired goal location. This is a trivial task when the environment is static. However, the operational environment of the robot is rarely static, and it often has many moving obstacles. The robot may encounter one, or many of these unknown and unpredictable moving obstacles. The robot will need to decide how to proceed when one of these obstacles is obstructing it's path. A method of dynamic replanning using RRT* is presented. The robot will modify it's current plan when an unknown random moving obstacle obstructs the path. Various experimental results show the effectiveness of the proposed method.

Keywords: Robotic Systems, System Modeling and Control, Design Methods
Abstract: Abstract—This paper presents a novel control method of extended virtual constraint to mimic human movement for a three-link planar robot with moving torso. Inspired by two supine yoga movements, the dynamic model of bipedal walker is modified accordingly, which enlarges application of generalized planar biped robot and provides a more stable and robust walking gait. Due to the continuity of kinematics and discreteness of impact, the walking motion is regarded as a hybrid system, whose zero dynamics determines the stable state of robot. Hence, a within-stride feedback controller is designed based on input-output linearization and extension of virtual constraint. Moreover, poincaré return map is adopted to analyze the stability of walking gait. The simulation results demonstrate the validity of proposed control law, leading to asymptotically stable walking with modified planar biped robot.

Keywords: Intelligent Transportation Systems, Machine Vision
Abstract: Monocular ORB-SLAM has been proved to be one of the best open-source SLAM method. However, it is still unsatisfying especially in low illumination indoor environment, which is caused by scale recovery and wrong feature matching. In this paper, we proposed a vehicle model based monocular ORB-SLAM method supplemented by April-Tag to improve the performance of original algorithm. This approach is practical when autonomous driving in low-light and less-feature environment like garages and tunnels. We achieve this by proposing a vehicle model based initialization method fusing April-Tag measurement to recover scale. During tracking procedure, the outliers ORB feature points will be removed by checking reprojection error calculated from April-Tag. In addition, considering vehicle model can only obtain 2D motion, the vertical transition is estimated from camera model. Afterwards, a local Bundle Adjustment(BA) is applied to optimize camera pose both from frame to frame and frame to keyframe which will reduce accumulative error of the vehicle model. Finally, a convincing result is obtained from the testing drive in a garage.

Keywords: Robotic Systems
Abstract: A novel hexapod-quadcopter robot was developed with multicopter flight hardware directly embedded in the hexapod legs. This paper discusses the locomotion implementations for walking and flying in addition to transitional procedures necessary to switch between these two modes of operation. The algorithms were programmed using Robot Operating System on the 3D printed robot and tested to verify feasibility and performance.

Keywords: Intelligent Transportation Systems, Service Systems & Organizations, Heuristic Algorithms
Abstract: Currently, the robot is playing an increasingly significant role in managing a warehouse. This paper proposes an optimal method to help a warehouse robot make task decisions, which aims at minimizing the whole cost of completing tasks. Firstly, Abstract Transition System (ATS) is used to model the warehouse environment, and Linear Temporal Logic (LTL) formula is used to formulate the tasks of warehouse robot. Then based on the ATS and the Buchi automaton translated from the LTL formula, a Min-cost Task Decision Algorithm is proposed to obtain the task decision for the warehouse robot. The decision includes the order and path to do the tasks.The effectiveness of the proposed method is validated through case studies with two kinds of tasks.

Keywords: Robotic Systems, Design Methods, Supervisory Control
Abstract: This paper deals with the off-line route planning of Automated Guided Vehicles (AGVs). We propose a conflict-free route planning approach for the AGVs control system in a warehouse system. The candidate routes are determined by using improved Dijkstra algorithm. The potential conflicts are detected and classified by comparing node coordinates and occupancy times. A self-adaptive strategy is implemented to resolve the potential conflicts in terms of conflict and mission class. Presented simulation results demonstrate efficiency of the proposed conflict-free route planning approach.

Keywords: Robotic Systems, Evolutionary Computation, Optimization
Abstract: The navigation relayed by multiple stations (NRMS) is an advanced cooperative navigation technology which relies on multiple different stations to sequentially guide a vehicle to its destination. This paper addresses the optimal path planning problem for the vehicle navigated by the NRMS technology (OPP-V-NRMS) which is a challenging hierarchical mixed-variable constrained optimization problem involving two coupling levels. To solve OPP-V-NRMS, we present two decoupling methods: the accurate method and the approximation method. The accurate method performs path planning for all possible arrangements, which is accurate but time-consuming. The approximation method only selects a few arrangements for path planning, which achieves a better tradeoff between solution quality and computational cost. In both decoupling methods, a differential evolution based (DE-based) path planning algorithm is proposed for path planning. Comparative experiments show that both methods can find a feasible and high-quality path for the vehicle while the approximation method brings about much lower computational cost.

Keywords: Robotic Systems, Human-Machine Cooperation & Systems, Multimedia Systems
Abstract: This study extends existing Rubber Hand Illusion (RHI) experiments to employ life-size full-body humanlike android robot to investigate body ownership illusion and the sense of agency. For this study, we designed a novel experimental setting. The android robot moved synchronously with a participant’s head and arm motion. Furthermore, a stereoscopic camera was mounted on the android’s head and the video stream from the camera was provided to a head mounted display (HMD) that the participant wore. Then, the participant and the robot were facing each other, so that the participant could see his/her own body in the HMD like a reflection in a mirror. During the experiment the participant was asked to touch his/her own body by the hands of an android robot. The results of our study confirmed that the body ownership process worked with the full body android robot. The results also showed that our system enabled the participants to feel the sense of agency to some extent.

Keywords: Cooperative Systems and Control, Robotic Systems, Swarm Intelligence
Abstract: In this paper, we use the combination of graph theory and consensus algorithm to realize the formation control of nonholonomic wheeled robots. A novel edge-weight function is designed so that the desired formation-shape can be achieved. In addition, the consensus problem is usually solved on the assumption that the robots are modeled as particle model, but this assumption is not suitable when we are dealing with real robots, so we design a novel algorithm to meet the nonholonomic constraints of wheeled robots. Finally, the effectiveness of the proposed method is verified by the simulation results of an example.

Keywords: Augmented Cognition, Human Factors, System Modeling and Control
Abstract: Although machine motion control has made remarkable progress by identifying rationally controllable points and by establishing one-to-one correspondence between the motion and the task, progress in human motion control is very slow. This is because humans move in multiple ways to achieve the same task. Machine motion is controlled from outside, and past researches on human motion control followed suit. But if we note that humans perform their movements by trial and error, we can develop another approach, i.e. internally controlled or proprioception approach. Although machine motion control emphasizes reproducibility, human motion control has several other significant contributions. It serves for strengthening situational awareness so that it is expected to reduce human errors due to disuse atrophy. And as humans make decisions themselves to adapt to the situation, we can secure more adaptability and such self-determination contributes to satisfy our human needs to grow and our intrinsic motivations. Thus, while machine motion control is more related to product value, we could enhance customers’ value through such processes. Therefore, we should throw another light on human motion control from the standpoint of adaptability and value creation. To achieve this goal, Mahalanobis Taguchi System is applied to provide a quantitative measure to help us evaluate our motions.

Keywords: Human Factors, Intelligent Transportation Systems, Human-Machine Cooperation & Systems
Abstract: The interaction between a human driver and an automated driving system may improve when the automation is designed in such a way that it behaves in a human-like manner. This paper introduces a human-like steering model, in which the driver adapts to the risk due to uncertainty in the environment. Current steering models take a risk-neutral approach, while the fields of economics and sensorimotor control suggest that humans exhibit risk-sensitive behavior. The proposed model uses a risk-sensitive optimal feedback control structure to predict steering behavior. The paper studies the effect of the risk-sensitivity parameter and compares the prediction of the risk-neutral and risk-sensitive controllers in a simulated abstraction of two scenarios: (a) driving while being subjected to lateral wind gusts and (b) overtaking an unpredictably swerving car. The simulation results show that the risk-sensitive model adapts to the uncertainty in the environment. Experimental data will be needed to validate the predictions of our model.

Keywords: Human Factors, Robotic Systems, Human-Machine Cooperation & Systems
Abstract: We investigate the effect of dominant and submissive movement strategies and a movement cue in a human-robot cooperation scenario on perceived predictability and trust. Four different movement strategies in proximal cooperation between a robot manipulator and a human participant were tested in an experiment in which participants had to arrange small objects in a shared workspace working on the same product as the robot. The features of the robot motion were characterized by dominance or a movement cue. The robot modifies its motion in two ways resulting in four different movement strategies: either it stops when the human is in danger of collision (submissive) or not (dominant), and either it performs a backing-off movement cue or not. The participants evaluated the movement strategies in terms of trust and predictability in a questionnaire. We found that the submissive backing-off movement strategy significantly enhanced the users’ trust compared to the dominant movement strategy without movement cue. Other strategies showed no significant differences in trust or predictability.

Keywords: Human Factors, Human Performance Modeling
Abstract: Cognitive load corresponds to the amount of working memory demanded while performing a certain task. Estimation of cognitive load is crucial to many domains and the usage of pupil size dilation to accomplish this is widely researched. However, existing approaches suffer severely as they are largely based on the raw pupil size. In this study, we aim to use the frequency domain analysis of the pupil size variations to get an insight of the load imposed. We propose a cognitive load metric based on the power and frequency relations at the mean frequency of the variation in pupil size. The stimulus used is a mental addition task which is designed in a manner to induce low and high cognitive loads on the participants. Results show good separation in the metric for the tasks inducing low and high mental workloads in contrast to the state of the art methods.

Keywords: Human Factors
Abstract: Within 5 to 10 years, conditionally automated driving systems may be available on the market. Even though these systems exempt drivers from driving tasks for periods of time, drivers are expected to take back control when the automation issues a so-called take-over request. This study investigated the interaction between take-over request modality and the type of non-driving task, regarding the driver’s reaction time. It was hypothesized that tasks which predominantly use a certain perceptual modality would yield increased reaction times when the take-over request was presented in that same modality. For example, auditory take-over requests were expected to be relatively ineffective in situations in which the driver is making a phone call. 101 participants, divided into three groups, performed one of three non-driving tasks, namely reading (i.e., visual task), calling (auditory task), or watching a video (visual/auditory task). Results showed that tactile and auditory take-over requests yielded faster reactions than visual take-over requests. However, the expected interaction between take-over modality and the dominant modality of the non-driving task was not found. As for self-reported usefulness and satisfaction, tactile take-over requests outperformed the auditory and visual ones. In conclusion, it seems that auditory and tactile stimuli are equally effective as take-over requests, regardless of the non-driving task. Further study into the effects of realistic non-driving related tasks is needed to identify which non-driving tasks are detrimental to safety in automated driving.

Keywords: Human Factors, Human-Machine Cooperation & Systems
Abstract: This paper investigates if sensory perceptions of orange drinks (e.g., acidity, thickness, wateriness) can be linked to physical measurements (e.g., pH, particle size, density). Using this information, manufactured drinks can be tailored according to consumer' desires by, for example, the consumer providing a sensory description of their preferred drink. Sensory perceptions of different juices are collected in a survey and used to determine 1) if consumers can distinguish between different drinks using the provided sensory descriptors, and 2) if the perceptions match to physical measurements of the drinks. Results show that most of the given sensory descriptors are useful in describing differences in orange drinks. Additionally, the perceived wateriness and thickness of the drinks can be predicted from measurements. However, the perceived acidity could not be reliably predicted. The results show that personally tailored orange beverages can be manufactured according to some of the consumer's desires and there is scope for future developments tailored to a wider range of drink attributes.

Keywords: Human Factors, Human-Machine Cooperation & Systems, System Modeling and Control
Abstract: This paper investigates the use of a variable haptic feedback for training a disturbance rejection task. The haptic feedback was designed as a Force-Stiffness feedback. Throughout the training, Force and Stiffness feedback are decreased to progressively give more control authority to the human operator. The training method was tested in a human-in-the-loop experiment. In the experiment, participants were split into three groups: variable haptic aid (VHA), constant haptic aid (CHA) and no haptic aid (NoHA). The VHA and CHA groups performed a first training phase with variable and constant haptic feedback respectively, followed by an evaluation phase without external aids. The NoHA group performed the entire experiment without external aids. Results showed that in the training phase both VHA and CHA groups performed better than NoHA group. In the evaluation phase though, only the VHA group obtained better performances than the NoHA group. Specifically, participants were able to quickly recover similar performances to those obtained at the end of the training phase. Thus, the variable haptic training proved to be more effective than the constant haptic training and manual control at helping participants learn the task.

Keywords: Human Factors, Wearable Computing
Abstract: In this paper, we evaluate methods of aggregating personal sensor data to estimate the degree of group stress. We compare the estimation accuracy of two aggregation methods, one without and one with personal distribution scaling. As a result of applying the data of 9 groups of people (105 people) to the methods, it is shown that the no-scaling method successfully estimates the degree of group stress better than the other (average error = 1.19, r = 0.964). At the conclusion of discussion, it is suggested that the method without scaling is valid because both the group stress state and method reflect the interaction among people.

Keywords: Human-Computer Interaction, Image Processing/Pattern Recognition, Human Factors
Abstract: In this paper, we propose a novel eye-tracking method that uses a multispectral camera to simultaneously track the pupil and recognize the iris. Our hybrid approach leverages existing methods, combining them so as to compensate for weaknesses present in each individual method when used alone. Significantly, our method allows for movements of the center of rotation of the eye to be taken into consideration, this having been treated as a static point in most of earlier studies. Additionally, our method allows for the diameter of the pupil to be measured quantitatively using just a single camera. To confirm the effectiveness of our method, we conduct two experiments, in which we estimate the area and shape of the iris, the point-of-gaze, and the size of the pupil. We go on to observe that the effectiveness of our proposed method is increased compared to previous methods, particularly in situations where the eye is moved to the extreme inner corner of its socket.

Keywords: Human Factors, Machine Learning, Information Visualization
Abstract: Decision support systems for network security represent a critical element in the safe operation of computer networks. Unfortunately, due to their complexity, it can be difficult to implement and empirically assess novel techniques for displaying networks. This paper details an open source adaptive user interface that hopes to fill this gap. This system supports agile development and offers a wide latitude for human factors and machine learning design modifications. The intent of this system is to serve as an experimental testbed for determining the efficacy of different human factors and machine learning initiatives on operator performance in network monitoring.

Keywords: Human Factors, Human-Machine Cooperation & Systems, Human-Machine Interface Web
Abstract: Nowadays, a lot of IT personnel have psychological distress. Meanwhile, there are a few counselors for helping them. To solve the problem, we proposed a counseling agent (CA) called CRECA (context respectful counseling agent). This agent listens to clients and promotes their reflection by context respectful namely context preserving way. To continue the conversation naturally or context respectfully towards clients’ further reflection, this is enhanced using body language of a robot to make CRECA more “human like”. Namely, as a focus of this paper, the robot nods at appropriate times during the dialog. This mimics a behavior often performed by Japanese in conversation. Thus, CRECA can become more “naturally”. This nodding behavior is called “unazuki” in Japanese. This body language expects to significantly help represent entire approval in CRECA as its paraphrasing does. Integrating an agent with a nodding robot was implemented and the experiment proved it is surely effective in Japanese counseling.

Keywords: Neural Networks and their Applications, Control of Uncertain Systems, Robotic Systems
Abstract: This paper proposes an adaptive control for a rigid-link, flexible-joint robot using the Cerebellar Model Articulation Controller (CMAC) and the backstepping method, which is a suitable method when joints are underdamped and exhibit a large amount of flexibility. A previously proposed robust weight update method, deemed the introspective method, is placed into a Lyapunov-stable framework. In the introspective method, each local CMAC cell measures the output error in its own domain and over the domain of several sequentially activated cells on the same CMAC array. The cell then votes on whether it appears its previous weight update has reduced this error or not. The sum of all votes from the activated cells determines whether weight updates continue. In order to ensure uniformly ultimately bounded signals, a robust CMAC operates in parallel using a conservative e-modification weight update. Simulations with a two link flexible-joint arm show significantly improved performance over e-modification and a model-based LQR control.

Keywords: Machine Vision, Image Processing/Pattern Recognition, Robotic Systems
Abstract: In the paper, we propose a rigid motion segmentation algorithm with the grid-based optical flow. The algorithm selects several adjacent points among grid-based optical flows to estimate motion hypothesis based on a so-called entropy and generates motion hypotheses between two images, thus separates objects which move independently of each other. The grid-based entropy is accumulated as a new motion hypothesis generated and the high value of entropy means that the motion has been estimated inaccurately in the corresponding grid. The motion hypothesis is estimated by three-dimensional rigid transformation and classified by the open-source implementation of density-based spatial clustering of applications with noise (DBSCAN). For the evaluation of the proposed algorithm, we use a self-made dataset captured by ASUS Xtion Pro live RGB-D camera. Our algorithm implemented in the unoptimized MATLAB code spends 170 ms of average computational time per frame, showing the potential for the application to the robust real-time visual odometry.

Keywords: Neural Networks and their Applications, Computational Intelligence
Abstract: The elderly people living alone or life of a patient face distress situations particularly in case of falling and becoming unable to ask for help. Fall in elderly people may result in head injury, broken hips, and bones that need immediate hospitalization to lower the mortality risk. During the last decade, several technological solutions were presented for early fall detection but most of them have critical limitations and are impeded by several environmental constraints. In this paper, we have analyzed the environmental sounds for early fall detection utilizing the fact that reflection of pain directly occurs through sound. The proposed framework first analyzes the environmental sounds by suppressing the silence zones in signals and distinguishing overlapping sound signals through hidden Markov model based component analysis (HMM-CA). The source separated components are then represented by acoustic local ternary patterns (acoustic-LTPs) by extending the existing ideas of acoustic local binary patterns (acoustic-LBPs). In the proposed work, we have also introduced the concept of rotation invariance through uniform patterns for audio signals that, arguably, is a fundamental requirement for an acoustic descriptor. Once the signal representation is completed, we classify the signals through SVM classifier. The performance of the proposed acoustic-LTP is evaluated against state-of-the-art methods and acoustic-LBP. Results clearly evince that proposed method is more powerful and reliable in terms of fall detection when compared against other methods.

Keywords: Machine Vision, Robotic Systems, Image Processing/Pattern Recognition
Abstract: This paper proposes a method that realizes moving object detection (MOD) and static obstacle detection (SOD) in real time utilizing the fisheye cameras of the around viewing system (AVM). The topview of the AVM is used to calculate the vehicles movement between two frames using homograph estimation. Image features are detected and tracked evenly using cell detection technique. Then the features are projected onto the unit sphere of the fisheye camera model and the epipolar constraint is used to discriminate moving features from static ones. Moving features are clustered into different objects according to their position and orientation. 3D position of the static feature is calculated using triangular principle and potential obstacle is defined as objects above the ground and near the vehicle. The experiment shows the proposed method is robust and accurate for MOD and SOD.

Keywords: Intelligent Internet Systems, Computational Intelligence, Cybernetics for Informatics
Abstract: C-Rank (contribution-based ranking) is a state-of-the-art algorithm for ranking web pages. It combines content and link information by introducing the concept of contribution, which implies how much a page contributes to improving the content quality of other pages. However, C-Rank suffers from taking infeasible time to reflect changes in World Wide Web to every page’s C-Rank score. In this paper, we propose an effective and efficient method to incrementally maintain C-Rank scores of terms in web pages. Our proposed method is carefully designed to selectively update C-Rank scores of specific pages without any accuracy loss, rather than re-computing all the C-Rank scores of all the terms in all the pages from the scratch. Our experimental results on real-world dataset confirm the effectiveness and efficiency of our proposed method.

Keywords: Machine Learning, Cooperative Systems and Control, Large-Scale System of Systems
Abstract: Coordination problems including miscoordination and relative overgeneralization are difficult to be overcome especially in dynamic and stochastic environments. In the practical scenario, there may be a large number of agents, and the interactions between agents may be sparse and unfixed. In this paper, we study the coordination problems and stochastic rewards under the social learning framework where there are a group of agents and each agent behaves independently and interacts with another agent randomly chosen from the group. We are looking for a learning technique that makes all agents learn a consistent optimal policy in a two agents game with pathology of coordination problems or stochastic rewards under such a framework. A new algorithm named Decentralized concurrent learning and cooperative policy exploration (DCL-CPE) is contributed, which possesses the ability to overcome the coordination problems and the stochastic rewards via local interaction under the social learning framework. Empirical results for several cooperative games are presented to show the superiority of our algorithm.

Keywords: Evolutionary Computation, Image Processing/Pattern Recognition, Heuristic Algorithms
Abstract: The paper introduces a proposal for an automated magnetic resonance (MR) image segmentation called Case-Based Genetic Algorithm Location-Dependent Image Classification (CBGA-LDIC) and presents its evaluation results. This method finds an appropriate cell set towards efficient image segmentation. It uses location-dependent image classification (LDIC), which is integrated by genetic algorithm (GA) combined with case based reasoning (CB). LDIC is a local heuristic, which defines multiple location-dependent classifiers. Each classifier is trained by Gaussian mixture model. CBGA-LDIC decomposes the whole image into some cells, makes a set of cells, and then trains classifiers. The method is applied to knee bones, because these bone formations are similar in their location. Therefore, good combinations of cells are useful and stored in case bases. To show, that this method produces better results that other ones and to find optimal parameters, some experiments have been performed and their results are presented in this paper.

Keywords: Machine Learning, Neural Networks and their Applications, System Modeling and Control
Abstract: This research concerned about an online learning algorithm of the group method of data handling based proportional-integral-derivative (GMDH-PID) controller that is effective for nonlinear systems. Although a lot of PID controllers have been mainly used in industrial systems, it is difficult to maintain a desired control performance only by a PID controller with fixed control parameters due to system nonlinearities. In order to deal with such systems, a GMDH-PID controller that can adjust PID parameters according to a system change was proposed, and its effectiveness was evaluated. The GMDH-PID controller can maintain good control performance by appropriately setting its weight coefficients in the GMDH network. However, these coefficients are determined in an offline manner, thus the GMDH-PID controller cannot adapt a system if unexpected system change is happened while controlling. This paper proposes an online tuning method of the GMDH-PID controller based on the adaptive moment estimation that is one of recent attracted optimization methods. Thanks to this method, the GMDH-PID controller can adapt to unknown system change, thus applicable rage of the controller is expanded. The effectiveness of the proposed method is demonstrated by simulation examples.

Keywords: Machine Vision, Robotic Systems
Abstract: The stripe laser based stereo vision is often used in robot vision-guided system in the eye-in-hand configuration. The 3D scene is reconstructed from many 3D stripes obtained in stripe laser based stereo vision. But 3D objects can not be recognized by 3D stripe information. In 3D cluttered scene, the recognition of 3D objects is also difficult due to the object pose and match. In fact, the video from camera of stripe laser based stereo vision can be benefit to recognize 3D objects. This paper proposes an approach of the object-oriented vision-guided robot that video segmentation, tracking and recognition are used to guide robot to reduce the complexity of 3D object detection, recognition and pose estimation. Experimental results demonstrate the effectiveness of the approach.

Keywords: Evolutionary Computation, Optimization, Robotic Systems
Abstract: In recent years, significant research has been conducted on grasp planning for multi-fingered robot hands. These studies have focused on determining how to obtain suitable grasps from among an infinite number of candidate grasps. This domain’s goal is successful application to unknown environment through adoption of the extracted grasps. Under difficult conditions, such as grasping a target object that is adjacent to other objects, manipulating robot hands by indicating grasping points has been insufficient. Instead, grasp strategies that construct movements using each finger’s joint servo controls and robot hand movements should be used. In addition, it is necessary to automatically acquire a variety of grasp strategies to apply to unknown environments. In this paper, we propose a method that automatically obtains grasp strategies using a real-coded genetic algorithm (RCGA), which is an evolutionary algorithm. This method derives grasp strategies by optimizing combinations and structures that consist of simple finger joint servo controls and robot hand movements. By applying our method to several objects on a simulator, we collected various grasp strategies capable of handling difficult conditions.

Keywords: System Modeling and Control, Computational Life Science, Brain-based Information Communications
Abstract: Human brain determines the ability of perceiving and behaving. Previous works have introduced network science and control theory to stimulate the brain states and functions. In this work, network controllability theory is utilized to study the structural controllability of both temporal and static functional brain networks. We find that only a few nodes are the required driver nodes to structurally control the static functional brain networks. Specially, some regions of interest (ROIs) in cerebellums with low connectivity play important roles in controlling functional brain networks. Structural controllability of temporal functional brain networks is more complicated. Control centrality of nodes which presents the ability to control other nodes does not only depend on the degree but also on the location of the nodes via studying the temporal functional brain network.

Keywords: System Modeling and Control
Abstract: Next generation non-volatile memory technologies draw attention recently as promising candidates for replacing conventional DRAM-based memory devices. By using the favorable features such as low energy consumption, non-volatility, and good scalability, the next generation non-volatile memory devices can replace conventional main memory and secondary storage layers. This paper proposes a hot-cold data filtering adapter with it management algorithm for the memory-storage unified system which uses phase change RAM (PRAM) devices. The proposed hot-cold data filtering adapter consisting of dual decoupled adaptive buffers can improve drawbacks of PRAM, such as slower read/write access latencies and limited life time compared to DRAM, enhance spatial/temporal localities, and optimize the data reusability by analyzing data access pattern. Experimental results show that the proposed architecture and its algorithm improves the miss rate by about 69.2% and write count is decreased by 96.4% compared with a uniform buffer of the same size.

Keywords: Intelligent Power Grid, Optimization, Cooperative Systems and Control
Abstract: In smart grids, demand-side management (DSM) is one of the important function for both customers and utility, since it can reduce the total electricity cost of each customer, meanwhile, alleviate the aggregate peak-to-average ratio (PAR) subjected to real-time pricing (RTP) policy. On the other hand, while bidirectional charging/discharging Plug-in Electric vehicles (PEV) become more general, the capability of storing electrical energy for load shifting may take smart grid to a next level. This works aims at integrating PEV into DSM system, which considers renewable energy and energy trading as well. As it comes to community, we design a fairness strategy to share PEV’s battery with neighbors to reduce the total electric cost and peak to average ratio (PAR). The simulation results show that the proposed DSM system not only meets the requirement of the PEV and reduce the cost for each household but also creates a win-win situation through the energy trading among homes based on consideration of both fairness and privacy protection in a residential community.

Keywords: Manufacturing Systems/Automation, Intelligent Green Production, System Modeling and Control
Abstract: This paper studies the energy characteristics with respect to process parameters from a systematic point of view, in terms of electricity and materials. A detail analysis of energy characteristics of a CNC machining system is firstly presented, based on which the calculation models of energy efficiency are formulated. Then the effects of important input process variables on energy and processing time are investigated by using S/N analysis. The results show different optimization trends for two kinds of specific energy consumption considered in this work and detail explanations of the trends are given afterwards.

Keywords: Large-Scale System of Systems, Cooperative Systems and Control, Infrastructure Systems & Services
Abstract: In the 21st century, urbanization as a mega-trend will create many megacities. These highly dense, large population centers will have to efficiently deliver essential services including, energy, water, mobility, manufactured goods, and healthcare. While these services may be treated independently, they are in reality interdependent, especially as the need for efficient resource utilization, and consequently integration. This presents a formidable engineering challenge as the modeling foundations for these services have traditionally been discipline specific. Furthermore, efforts to integrate these modeling foundations have often adopted simplifying constraints which have limited applicability to the emerging challenge of smart cities. This paper collates an emerging “hetero-functional graph theory” for potential application to integrated smart city infrastructure models. It has been recently demonstrated in several application domains. The paper concludes with the construction of a hetero-functional graph for a smart city model consisting of an integrated electricity, water, and transportation system. Such a graph has the potential for dynamic modeling, resilience analysis, and integrated decision-making.

Keywords: System Modeling and Control, Fuzzy Systems and their applications
Abstract: This paper takes advantages from probability theory and fuzzy modeling. We use probability theory to overcome some common problems in data based modeling methods. A probability based clustering method is proposed to partition the hidden features, and extract fuzzy rules with probability measurement. An optimization method are applied to train the consequent part of the fuzzy rules and the probability parameters. The proposed method is validated with two benchmark problems.

Keywords: System Modeling and Control
Abstract: This paper focuses on identification of systems with rate saturation nonlinearity, considering measurement and process noises. A methodology is proposed to estimate the parameters of linear dynamics along with the upper and lower limits of rate saturation, using only system input and output. The methodology consists of four correlative parts which sequentially are choosing sine sweep signal with appropriate amplitude and frequency as input to excite the system sufficiently, designing a Kalman filter based on the constant rate model to obtain rate optimal estimation, suggesting a window scanning and filtrating method which deals with rate estimation to identify rate saturation limits, and applying the bias compensation recursive least squares with valid input and output data filtrated by the estimated rate limits to identify linear dynamics. Simulation results of a position servo system with rate saturation are presented to illustrate the validity of the proposed technique.