Akshansh Gupta

Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods

In the recent years, the research community has shown interest in the development of brain–computer interface applications which assist physically challenged people to communicate with their brain electroencephalogram (EEG) signal. Representation of these EEG signals for mental task classification in terms of relevant features is important to achieve higher performance in terms of accuracy and computation time. For feature extraction from the EEG, empirical mode decomposition and wavelet transform are more appropriate as they are suitable for the analysis of non-linear and non-stationary time series signals. However, the size of the feature vector obtained from them is huge and may hinder the performance of mental task classification. To obtain a minimal set of relevant and non-redundant features for classification, six popular multivariate filter methods have been investigated which are based on different criteria: distance measure, causal effect and mutual information. Experimental results demonstrate that the classification accuracy improves while the computation time reduces considerably with the use of each of the six multivariate feature selection methods. Among all the combinations of feature extraction and selection methods that are investigated, the combination of wavelet transform and linear regression performs the best. Ranking analysis and statistical tests are also performed to validate the empirical results.

A review of clustering techniques and developments

This paper presents a comprehensive study on clustering: exiting methods and developments made at various times. Clustering is defined as an unsupervised learning where the objects are grouped on the basis of some similarity inherent among them. There are different methods for clustering the objects such as hierarchical, partitional, grid, density based and model based. The approaches used in these methods are discussed with their respective states of art and applicability. The measures of similarity as well as the evaluation criteria, which are the central components of clustering, are also presented in the paper. The applications of clustering in some fields like image segmentation, object and character recognition and data mining are highlighted.

Edge of Things: The Big Picture on the Integration of Edge, IoT and the Cloud in a Distributed Computing Environment

A centralized infrastructure system carries out existing data analytics and decision-making processes from our current highly virtualized platform of wireless networks and the Internet of Things (IoT) applications. There is a high possibility that these existing methods will encounter more challenges and issues in relation to network dynamics, resulting in a high overhead in the network response time, leading to latency and traffic. In order to avoid these problems in the network and achieve an optimum level of resource utilization, a new paradigm called edge computing (EC) is proposed to pave the way for the evolution of new age applications and services. With the integration of EC, the processing capabilities are pushed to the edge of network devices such as smart phones, sensor nodes, wearables, and on-board units, where data analytics and knowledge generation are performed which removes the necessity for a centralized system. Many IoT applications, such as smart cities, the smart grid, smart traffic lights, and smart vehicles, are rapidly upgrading their applications with EC, significantly improving response time as well as conserving network resources. Irrespective of the fact that EC shifts the workload from a centralized cloud to the edge, the analogy between EC and the cloud pertaining to factors such as resource management and computation optimization are still open to research studies. Hence, this paper aims to validate the efficiency and resourcefulness of EC. We extensively survey the edge systems and present a comparative study of cloud computing systems. After analyzing the different network properties in the system, the results show that EC systems perform better than cloud computing systems. Finally, the research challenges in implementing an EC system and future research directions are discussed.

Relevant feature selection from EEG signal for mental task classification

In last few years, the research community has shown interest in the development of Brain Computer Interface which may assists physically challenged people to communicate with the help of brain signal. The two important components of such BCI system are to determine appropriate features and classification method to achieve better performance. In literature, Empirical Mode Decomposition is suggested for feature extraction from EEG which is suitable for the analysis of non-linear and non-stationary time series. However, the features obtained from EEG may contain irrelevant and redundant features which make them inefficient for machine learning. Relevant features not only decrease the processing time to train a classifier but also provide better generalization. Hence, relevant features which provide maximum classification accuracy are selected using ratio of scatter matrices, Chernoff distance measure and linear regression. The performance of different mental task using different measures used for feature selection is compared and evaluated in terms of classification accuracy. Experimental results show that there is significant improvement in classification accuracy with features selected using all feature selection methods and in particular with ratio of scatter matrices.

A three phase approach for mental task classification using EEG

The Brain Computer Interface provides a channel of communication to physically challenged individuals who have fully or partially lost the power to interact with their surroundings. The strength of a BCI system lies in its ability to determine the appropriate features for a given task and to be able to correctly classify a task amid many other mental tasks. The electroencephalogram (EEG) is a cost effect and efficient means to capture the intent of a person with motor disorder. Wavelet decomposition for feature extraction from EEG is suitable for the analysis of non-linear and non-stationary time series. Hence, Wavelet decomposition of EEG is used in this study to form a feature set. Of the extracted features, a subset of discriminatory and relevant features is selected using ratio of scatter matrices, Chernoff distance measure and linear regression. The performance of different mental tasks using the selected features is compared and evaluated in terms of classification accuracy and the dimension of features. Experimental results on publicly available data show that there is significant improvement in classification accuracies with different feature selection methods. Linear regression performs better in comparison to other two methods and Support Vector Machine requires lesser number of features to build the model.

Fuzzy clustering-based feature extraction method for mental task classification

A brain computer interface (BCI) is a communication system by which a person can send messages or requests for basic necessities without using peripheral nerves and muscles. Response to mental task-based BCI is one of the privileged areas of investigation. Electroencephalography (EEG) signals are used to represent the brain activities in the BCI domain. For any mental task classification model, the performance of the learning model depends on the extraction of features from EEG signal. In literature, wavelet transform and empirical mode decomposition are two popular feature extraction methods used to analyze a signal having non-linear and non-stationary property. By adopting the virtue of both techniques, a theoretical adaptive filter-based method to decompose non-linear and non-stationary signal has been proposed known as empirical wavelet transform (EWT) in recent past. EWT does not work well for the signals having overlapped in frequency and time domain and failed to provide good features for further classification. In this work, Fuzzy c-means algorithm is utilized along with EWT to handle this problem. It has been observed from the experimental results that EWT along with fuzzy clustering outperforms in comparison to EWT for the EEG-based response to mental task problem. Further, in case of mental task classification, the ratio of samples to features is very small. To handle the problem of small ratio of samples to features, in this paper, we have also utilized three well-known multivariate feature selection methods viz. Bhattacharyya distance (BD), ratio of scatter matrices (SR), and linear regression (LR). The results of experiment demonstrate that the performance of mental task classification has improved considerably by aforesaid methods. Ranking method and Friedman’s statistical test are also performed to rank and compare different combinations of feature extraction methods and feature selection methods which endorse the efficacy of the proposed approach.

Distinguishing Two Different Mental States of Human Thought Using Soft Computing Approaches

Electroencephalograph (EEG) is useful modality nowadays which is utilized to capture cognitive activities in the form of a signal representing the potential for a given period. Brain–Computer Interface (BCI) systems are one of the practical application of EEG signal. Response to mental task is a well-known type of BCI systems which augments the life of disabled persons to communicate their core needs to machines that can able to distinguish among mental states corresponding to thought responses to the EEG. The success of classification of these mental tasks depends on the pertinent set formation of features (analysis, extraction, and selection) of the EEG signals for the classification process. In the recent past, a filter-based heuristic technique, Empirical Mode Decomposition (EMD), is employed to analyze EEG signal. EMD is a mathematical technique which is suitable to analyze a nonstationary and nonlinear signal such as EEG. In this work, three-stage feature set formation from EEG signal for building classification model is suggested to distinguish different mental states. In the first stage, the signal is broken into a number of oscillatory functions through EMD algorithm. The second stage involves compact representation in terms of eight different statistics (features) obtained from each oscillatory function. It has also observed that not all features are relevant, therefore, there is need to select most relevant features from the pool of the formed features which is carried out in the third stage. Four well-known univariate feature selection algorithms are investigated in combination with EMD algorithm for forming the feature vectors for further classification. Classification is carried out with help of learning the support vector machine (SVM) classification model. Experimental result on a publicly available dataset shows the superior performance of the proposed approach.

Hurst Exponent as a New Ingredient to Parametric Feature Set for Mental Task Classification

Electroencephalograph (EEG) is a popular modality to capture signals associated with brain activities in a given time window. One of the powerful applications of EEG signal is in developing Brain–Computer Interface (BCI) systems. Response to mental tasks is one of BCI systems which helps disabled persons to communicate their need to the machines through signals related to particular thought also known as Mental Task Classification (MTC). The success of application depends on the efficient analysis of these signals for further classification. Empirical Mode Decomposition (EMD), a filter-based heuristic technique, is utilized to analyze EEG signal in the recent past. In this work, feature extraction from the EEG signal is done in two stages. In the first stage, the signal is broken into a number of oscillatory functions by means of EMD algorithm. The second stage involves compact representation in terms of eight different statistics (features) obtained from each function. Hurst Exponent as a new ingredient to parametric feature set is investigated to check its suitability for MTC. Support Vector Machine (SVM) classifier is utilized to develop a classification model and to validate the proposed approach for feature construction for classifying the different mental tasks. Experimental result on a publicly available dataset shows the superior performance of the proposed approach in comparison to the state-of-the-art methods.

Voice Navigation Effects on Real-World Lane Change Driving Analysis Using an Electroencephalogram

Improving the degree of assistance given by in-car navigation systems is an important issue for the safety of both drivers and passengers. There is a vast body of research that assesses the usability and interfaces of the existing navigation systems but very few investigations study the impact on the brain activity based on navigation-based driving. In this paper, a real-world experiment is designed to acquire the electroencephalography (EEG) and in-car information to analyze the dynamic brain activity while the driver is performing the lane-changing task based on the auditory instructions from an in-car navigation system. The results show that auditory cues can influence the speed and increase the frontal EEG delta and beta power, which is related to motor preparation and decision making during a lane change. However, there were no significant results on the alpha power. A better lane-change assessment can be obtained using specific vehicle information (lateral acceleration and heading angle) with EEG features for future naturalized driving study.

Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification

Brain Computer Interface (BCI), a direct pathway between the human brain and computer, is one of the most pragmatic applications of EEG signal. The electroencephalograph (EEG) signal is one of the monitoring techniques to observe brain functionality. Mental Task Classification (MTC) based on EEG signals is a demanding BCI. Success of BCI system depends on the efficient analysis of these signals. Empirical Mode Decomposition (EMD) is a filter based heuristic technique which is utilized to analyze EEG signal in recent past. There are several variants of EMD algorithms which have their own merits and demerits. In this paper, we have explored three variants of EMD algorithms named Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) on EEG data for MTC-based BCI. Features are extracted from EEG signal in two phases; in the first phase, the signal is decomposed into different oscillatory functions with the help of different EMD algorithms and eight different parameters (features) are calculated for each function for compact representation in the second phase. These features are fed into Support Vector Machine (SVM) classifier to classify the different mental tasks. We have formulated two different types of MTC, the first one is binary and second one is multi-MTC. The proposed work outperforms the existing work for both binary and multi mental tasks classification.