Search

Over the past decade, emotion detection using rhythmic brain activity has become a critical area of research. The asymmetrical brain activity has garnered the most significant level of research attention due to its implications for the study of emotions, including hemispheric asymmetry or, more generally, asymmetrical brain activity. This study aimed at enhancing the accuracy of emotion detection using Electroencephalography (EEG) brain signals. This happens by identifying electrodes where relevant brain activity changes occur during the emotions and by defining pairs of relevant electrodes having asymmetric brain activities during emotions. Experimental results showed that the proposed method is highly competitive compared with existing studies of multi-class emotion recognition. These results were improved by processing not the whole EEG signals but by focusing on fragments of the signals, called epochs, which represent the instants where the excitation is maximum during emotions. The epochs were extracted using the zero-time windowing method and the numerator group-delay function.

Recognizing emotions using biological brain signals requires accurate and efficient signal processing and feature extraction methods. Existing methods use several techniques to extract useful features from a fixed number of electroencephalography (EEG) channels. The primary objective of this study was to improve the performance of emotion recognition using brain signals by applying a novel and adaptive channel selection method that acknowledges that brain activity has a unique behavior that differs from one person to another and one emotional state to another. Moreover, we propose identifying epochs, which are the instants at which excitation is maximum, during the emotion to improve the system’s accuracy. We used the zero-time windowing method to extract instantaneous spectral information using the numerator group-delay function to accurately detect the epochs in each emotional state. Different classification scheme were defined using QDC and RNN and evaluated using the DEAP database. The experimental results showed that the proposed method is highly competitive compared with existing studies of multi-class emotion recognition. The average accuracy rate exceeded 89%. Compared with existing algorithms dealing with 9 emotions, the proposed method enhanced the accuracy rate by 8%. Moreover, experiment shows that the proposed system outperforms similar approaches discriminating between 3 and 4 emotions only. We also found that the proposed method works well, even when applying conventional classification algorithms.

Contrary to popular belief that only the frontal lobe is concerned with emotions, recent neuroscience experiments show that in each emotional state, some of the brain lobes fired clearly whereas some did not. Unlike most of the previous works, which focused on choosing a fixed set of electrodes to detect emotions, this work presents a novel approach that consists of investigating the cerebral activity while experiencing emotions to identify the brain lobes that are showing significant and relevant changes. The identification process of relevant brain lobes is adaptive as the brain activity varies from one person to another and differs from one lobe to another during the same emotional state. The electrodes of the selected brain lobes will be tuned before being used as resources to extract the features that are required for the proposed three phases classification process. Using a clustering technique, the tuning process excludes every electrode that hardly separates between relevant and irrelevant rhythmic brain changes. The results show that the proposed method outperforms all previous approaches. Compared to the best performance obtained by previous studies, the proposed method enhanced the accuracy of both valence and arousal dimensions by 5%. Besides, the accuracy of the dominance dimension was improved by 2%.

There is a wide area of application that uses cerebral activity to restore capabilities for people with severe motor disabilities, and actually the number of such systems keeps growing. Most of the current BCI systems are based on a personal computer. However, there is a tremendous interest in the implementation of BCIs on a portable platform, which has a small size, faster to load, much lower price, lower resources, and lower power consumption than those for full PCs. Depending on the complexity of the signal processing algorithms, it may be more suitable to work with slow processors because there is no need to allow excess capacity of more demanding tasks. So, in this review, we provide an overview of the BCIs development and the current available technology before discussing experimental studies of BCIs.

A stochastic model is introduced that accurately models collisions in Flying Ad Hoc wireless Networks (FANETs) where Unmanned Aerial Vehicles (UAVs) are flying within the same shared 3D airspace. The model has two input parameters, the number of flying UAVs and the average time for an arbitrary UAV to come into contact with another UAV (the inter contact time). Using only these two parameters, we provide simple, yet accurate closed-form expressions for different collision related metrics such as safety periods, survival probabilities and number of collisions. Two scenarios are particularly considered. The first assumes that UAVs are equipped with perfect collision detection and avoidance capabilities. This is essentially to answer the question of whether detection and resolution tools are required for a given UAVs fleet to accomplish its mission. The second scenario assumes that small UAVs cannot satisfy the requirements of collision detection and avoidance equipage due to their size, weight or power constraints. While the number of deployed UAVs is easily known, the setup of the inter contact time is rather problematic for the end user (space controller) of the system. To this end, we developed a generic simple expression of the inter contact time to ease the administration task. This generic expression is then instantiated to two mobility models. Extensive simulations based on OMNeT++ are used to validate the obtained analytical results. The simulation results are shown to be in a remarkable agreement with those of the conducted mathematical analysis.

The advancement of assistive technologies toward the restoration of the mobility of paralyzed and/or amputated limbs will go a long way. Herein, we propose a system that adopts the brain-computer interface technology to control prosthetic fingers with the use of brain signals. To predict the movements of each finger, complex electroencephalogram (EEG) signal processing algorithms should be applied to remove the outliers, extract features, and be able to handle separately the five human fingers. The proposed method deals with a multi-class classification problem. Our machine learning strategy to solve this problem is built on an ensemble of one-class classifiers, each of which is dedicated to the prediction of the intention to move a specific finger. Regions of the brain that are sensitive to the movements of the fingers are identified and located. The average accuracy of the proposed EEG signal processing chain reached 81% for five subjects. Unlike the majority of existing prototypes that allow only one single finger to be controlled and only one movement to be performed at a time, the system proposed will enable multiple fingers to perform movements simultaneously. Although the proposed system classifies five tasks, the obtained accuracy is too high compared with a binary classification system. The proposed system contributes to the advancement of a novel prosthetic solution that allows people with severe disabilities to perform daily tasks in an easy manner.

Background: The advances in assistive technologies will go a long way towards restoring the mobility of paralyzed and/or amputated limbs. In this paper, we propose a system that adopts the brain-computer interface ( BCI ) technology to control prosthetic fingers by thoughts. To predict the movements of each finger, a complex EEG signal processing algorithms should be applied in order to remove the outliers , to extract feature, to discriminate between the fingers and to control prosthesis's finger. The proposed method discriminates between the five human fingers. So a multi -classification problem based on ensemble of one class-classifier is applied where each classifier predicts the intention to move one finger. At the end, an adapted machine learning strategy is proposed to predict movements of multiple fingers at the same time. Results: The sensitive regions of the brain related to finger movements are identified and located. The proposed EEG signal processing chain, based on ensemble of one class-classifier, reach a classification accuracy of 81 \ % for five subjects according to the online approach. Unlike most of the existing prototypes that allow to control only one single finger and to perform only one movement at a time by the dedicated finger, our proposed system will enable multiple fingers to perform movements simultaneously. Despite that the proposed system classifies a five tasks, the obtained accuracy is too high compared to a binary classification system. Conclusion: The proposed system contributes to the advancement of a prosthetic allowing people with severe disabilities to do the daily tasks easily.

While existing localization approaches mainly focus on enhancing the accuracy, particular attention has recently been given to reducing the localization algorithm implementation costs. To obtain a tradeoff between location accuracy and implementation cost, recursive localization approaches are being pursued as a cost-effective alternative to the more expensive localization approaches. In the recursive approach, localization information increases progressively as new nodes compute their positions and become themselves reference nodes. A strategy is then required to control and maintain the distribution of these new reference nodes. The lack of such a strategy leads, especially in high density networks, to wasted energy, important communication overhead and even impacts the localization accuracy. In this paper, the authors propose an efficient recursive localization approach that reduces the energy consumption, the execution time, and the communication overhead, yet it increases the localization accuracy through an adequate distribution of reference nodes within the network.

International audience; The Internet of Things (IoT) ecosystem includes a plethora of devices equipped with heterogeneous communication interfaces. They exhibit different mobility patterns and hardware constraints as memory, battery and processing power. On the other hand, IoT applications are overlayed on top of these constrained-devices imposing stringent requirements in term of data availability, data coherence, and response latency. To cope with these challenges, Named Data Networking (NDN) architecture is positioned in the middle layer to act as the networking layer. By providing easy data access thanks to the unique and location-independent content names, in-network caching and name-based routing, NDN expects to hide from IoT applications the complexity and diversity of the underlying Things by adapting the network operation to their features. In this paper, we focus on data availability requirements threatened by high IoT network dynamics related to sensors mobility. We address the producer mobility issue in NDN/IoT networks using the routing-based approach. We propose a novel and efficient forwarding algorithm named AFIRM in order to support producer mobility, and compare its performances to those of other relevant solutions based on the routing approach.

While existing localization approaches mainly focus on enhancing the accuracy, particular attention has recently been given to reducing the localization algorithm implementation costs. To obtain a tradeoff between location accuracy and implementation cost, recursive localization approaches are being pursued as a cost-effective alternative to the more expensive localization approaches. In the recursive approach, localization information increases progressively as new nodes compute their positions and become themselves reference nodes. A strategy is then required to control and maintain the distribution of these new reference nodes. The lack of such a strategy leads, especially in high density networks, to wasted energy, important communication overhead and even impacts the localization accuracy. In this paper, the authors propose an efficient recursive localization approach that reduces the energy consumption, the execution time, and the communication overhead, yet it increases the localization accuracy through an adequate distribution of reference nodes within the network.

Epilepsy is known as a brain disorder characterized by recurrent seizures. The development a system that able to predict seizure before its coming has several benefits such as allowing early treatment or even preventing the seizure. In this article, we propose a seizure prediction algorithm based on extracting Shannon entropy from electroencephalography (EEG) signals. K-nearest neighbor (KNN) method is used to continuously monitor the EEG signals by comparing with normal and pre-seizure baselines to predict the upcoming seizure. Both baselines are continuously updated based on the most recent prediction result using distance-based method. Our proposed algorithm is able to predict correctly 42 from 55 seizures (76 %), tested using up to 570 hours EEG taken from MIT dataset. With its simplicity and fast processing time, the proposed algorithm is suitable to be implemented in embedded system or mobile application that has limited processing resources.Â

Web access and web resources open many horizons, their usage increases in all life aspects including government, education, commerce and entertainment, where the key to such resources lies in Web browsers. Acknowledging the importance of universal accessibility to web resources, the W3C has developed a series of guidelines into a Web Accessibility Initiative (WAI), with the goal of providing access to web resources for people with disabilities. In order to bridge the gap in the digital divide between the disabled and the non-disabled people, the authors believe that the development of novel assistive technologies using new human-computer interfaces will go a long way towards achieving this lofty goal. In this paper, they present a P300 Electroencephalography Brain-controlled Web browser to enhance the accessibility of people with severe motor disabilities to Web resources. It enhances their interaction with the Web taking their needs into account. The proposed Web browser satisfies the Mankoff's requirements of a system that would “allow true web access.”

Background Brain–computer interface (BCI) is a communication pathway applied for pathological analysis or functional substitution. BCI based on functional substitution enables the recognition of a subject's intention to control devices such as prosthesis and wheelchairs. Discrimination of electroencephalography (EEG) trials related to left- and right-hand movements requires complex EEG signal processing to achieve good system performance. New method In this study, a novel dynamic and self-adaptive algorithm (DSAA) based on the least-squares method is proposed to select the most appropriate feature extraction and classification algorithms couple for each subject. Specifically, the best couple identified during the training of the system is updated during online testing in order to check the stability of the selected couple and maintain high system accuracy. Results Extensive and systematic experiments were conducted on public datasets of 17 subjects in the BCI-competition and the results show an improved performance for DSAA over other selected state-of-the-art methods. Comparison with existing methods The results show that the proposed system enhanced the classification accuracy for the three chosen public datasets by 8% compared to other approaches. Moreover, the proposed system was successful in selecting the best path despite the unavailability of reference labels. Conclusions Performing dynamic and self-adaptive selection for the best feature extraction and classification algorithm couple increases the recognition rate of trials despite the unavailability of reference trial labels. This approach allows the development of a complete BCI system with excellent accuracy.

Although recursive localization approaches are efficiently used in wireless sensor networks (WSNs), their application leads to increased energy consumption caused by the important communication overhead necessary to achieve the localization task. Indeed, localization information coverage increases iteratively as new nodes estimate their locations and become themselves new reference nodes. However, the uncontrollable number evolution of such nodes leads, especially in high density networks, to wasted energy, important communication overhead and even impacts the localization accuracy due the adverse effects of error propagation and accumulation. This chapter proposes an efficient recursive localization (ERL) approach that develops a new reliable reference selection strategy to ensure a better distribution of the reference nodes in the network. ERL improves localization accuracy without incurring any additional cost. It allows conserving the energy and consequently prolonging the WSN life time.

Background Brain–computer interface (BCI) is a new communication pathway for users with neurological deficiencies. The implementation of a BCI system requires complex electroencephalography (EEG) signal processing including filtering, feature extraction and classification algorithms. Most of current BCI systems are implemented on personal computers. Therefore, there is a great interest in implementing BCI on embedded platforms to meet system specifications in terms of time response, cost effectiveness, power consumption, and accuracy. New-method This article presents an embedded-BCI (EBCI) system based on a Stratix-IV field programmable gate array. The proposed system relays on the weighted overlap-add (WOLA) algorithm to perform dynamic filtering of EEG-signals by analyzing the event-related desynchronization/synchronization (ERD/ERS). The EEG-signals are classified, using the linear discriminant analysis algorithm, based on their spatial features. Results The proposed system performs fast classification within a time delay of 0.430 s/trial, achieving an average accuracy of 76.80% according to an offline approach and 80.25% using our own recording. The estimated power consumption of the prototype is approximately 0.7 W. Comparison-with-existing-method Results show that the proposed EBCI system reduces the overall classification error rate for the three datasets of the BCI-competition by 5% compared to other similar implementations. Moreover, experiment shows that the proposed system maintains a high accuracy rate with a short processing time, a low power consumption, and a low cost. Conclusions Performing dynamic filtering of EEG-signals using WOLA increases the recognition rate of ERD/ERS patterns of motor imagery brain activity. This approach allows to develop a complete prototype of a EBCI system that achieves excellent accuracy rates.

Web services allow developers to create, generate and compose them at runtime. However, a single web service is not sufficient to achieve most of user demands in its own. This gives rise to the concept of web services composition of is an appropriate solution to maximize the benefits of web services. Web services composition has received a great attention from different communities. A number of different semantic standards/specifications have been proposed to tackle this issue. These standards are Ontology Web Language and Web Service Modeling Ontology. In this paper, we provide an overview of these standards and present a comparison between them. We also overview different applications that have developed based on each of these standards and present comparisons among them.

Service-oriented computing has emerged as the state-of-the-art distributed computing model for loosely coupled service-centric business applications. Specifically, service-oriented computing techniques allow organizations to compose Web services. Indeed, the organizational capacity to compose Web services has received much interest, particularly with respect to supporting business-to-business or enterprise application integration. In this paper, we present a system that proposes to adopt service composition as a new approach to integrate data from various data sources. We specify the business process description language as well as the service composition engine that supports the proposed language. We also present different strategies for executing a composite data service call. Copyright © 2013 John Wiley & Sons, Ltd.

Over the last few decades, brain signals have been significantly exploited for brain-computer interface (BCI) applications. In this paper, we study the extraction of features using event-related desynchronization/synchronization techniques to improve the classification accuracy for three-class motor imagery (MI) BCI. The classification approach is based on combining the features of the phase and amplitude of the brain signals using fast Fourier transform (FFT) and autoregressive (AR) modeling of the reconstructed phase space as well as the modification of the BCI parameters (trial length, trial frequency band, classification method). We report interesting results compared with those present in the literature by utilizing sequential forward floating selection (SFFS) and a multi-class linear discriminant analysis (LDA), our findings showed superior classification results, a classification accuracy of 86.06% and 93% for two BCI competition datasets, with respect to results from previous studies.

Sensorimotor rhythms (SMRs) caused by motor imagery are key issues for subject with severe disabilities when controlling home devices. However, the development of such EEG-based control system requires a great effort to reach a high accuracy in real-time. Furthermore, BCIs have to confront with inter-individual variability, imposing to the parameters of the methods to be adapted to each subjects. In this paper, we propose a novel EEG-based solution to classify right and left hands(RH and LH) thoughts. Our approach integrates adaptive filtering techniques customized for each subject during the training phase to increase the accuracy of the proposed system. The validation of the proposed architecture is conducted using existing data sets provided by BCI-competition and then using our own on-line validation platform experienced with four subjects. Common Spatial Pattern (CSP) is used for feature extraction to extract features vector from µ and I² bands. These features are classified by the Linear Discriminant Analysis (LDA) algorithm. Our prototype integrates the Open-BCI acquisition system with 8 channels connected to Matlab environment in which we integrated all EEG signal processing including the adaptive filtering. The proposed system achieves 80.5% of classification accuracy, which makes approach a promising method to control an external devices based on the thought of LH and RH movement.

The General Purpose GPU computational model changes the way parallel processing can be achieved. It is becoming more attractive to carry out parallel tasks on GPU devices. The sequential part of the application runs on the CPU whereas the computationally-intensive part is accelerated by the GPU. GPUs provide a multithreaded high level of parallelism with hundreds of cores. For high performance computing developers, the GPU cores offer a higher magnitude order of raw computation power than CPU. In this paper we propose an efficient parallel programming framework based on the GPU devices. This framework adopts the Gamma formalism as an abstract model for making parallelism less difficult. The software developer has only to specify the action to be curried-out on any atomic portion of data. The framework will then run the given action simultaneously on the GPU cores.

Web services are loose-coupled, which allows developers to create, generate and compose them at runtime. But, single Web service isn't sufficient to achieve most of user demand in the current period. Therefore, composition of Web services is the appropriate solution and it's the best way to deal with various user requests. It has received a great attention from different communities. A number of different standards/specifications have been proposed to tackle this issue. These standards are Ontology Web Language, Web Service Modeling Ontology, Business Process Modeling Language, Web Services Business Process Execution Language, Web Service Choreography Interface and Web Service - Choreography Description Language. In this paper, we provide an overview of different applications that have been developed based on each of these standards, and present three comparisons between those applications along with the popularity of Web search for them. Refereed/Peer-reviewed

The use of Web services as a standard technology facilitates seamless business-to-business (B2B) interaction and the process of integrating various systems and applications. It enables mass knowledge distribution by providing a standard way of exposing data sources and applications/systems as Web services. These services can be created/generated, updated, and composed at runtime because they are loosely coupled. Web service composition provides the ability to compose services by manually or automatically generating a service composition plan in order to achieve the business goal, resolve a scientific issue/problem or provide new service functionality. They are reusable services that can be used to implement a business process. Web service composition can be achieved via two models: dynamic and static. This paper introduces taxonomy of Web service composition models and approaches, and provides a survey of Web service composition models and their approaches. Additionally, we present comparisons of different models and approaches for each model.

The evolution of distributed computing has made sharing of data sources an urgent necessity at the present time. It is desired to benefit from distributed data sources that spread across a network. Efforts have been made by researchers and private companies to propose approaches for accessing remote, heterogeneous and autonomous data sources to share them across a network. Other efforts are looking at these approaches and the concepts in them with the aim of developing applications in both centralized and decentralized environments to provide access to and sharing of data sources. In this paper, we review two data sharing approaches that have been proposed, namely Transaction Processing Monitors and Resource Description Framework. For each approach, we will present its architecture, limitations and problems, as well as applications that have been developed based on its concepts. © 2011 IEEE Refereed/Peer-reviewed