Performance analysis of left/right hand movement classification from EEG signal by intelligent algorithms

Abstract

Brain Computer interfaces (BCI) has immense potentials to improve human lifestyle including that of the disabled. BCI has possible applications in the next generation human-computer, human-robot and prosthetic/assistive devices for rehabilitation. The dataset used for this study has been obtained from the BCI competition-II 2003 databank provided by the University of Technology, Graz. After pre-processing of the signals from their electrodes (C3 & C4), the wavelet coefficients, Power Spectral Density of the alpha and the central beta band and the average power of the respective bands have been employed as features for classification. This paper presents a comparative study of different classification methods including linear discriminant analysis (LDA), Quadratic discriminant analysis (QDA), k-nearest neighbor (KNN) algorithm, linear support vector machine (SVM), radial basis function (RBF) SVM and naive Bayesian classifiers algorithms in differentiating the raw EEG data obtained, into their associative left/right hand movements. Performance of left/right hand classification is studied using both original features and reduced features. The feature reduction here has been performed using Principal component Analysis (PCA). It is as observed that RBF kernelised SVM classifier indicates the highest performance accuracy of 82.14% with both original and reduced feature set. However, experimental results further envisage that all the other classification techniques provide better classification accuracy for reduced data set in comparison to the original data. It is also noted that the KNN classifier improves the classification accuracy by 5% when reduced features are used instead of the original.

Executed Movement Using EEG Signals through a Naive Bayes Classifier

“…The expert uses the components with high LI to compose the set of features. Moreover, same spectral components used by [29,[45][46][47] to classify EEG signals are suggested as features. In order to reach a good spectral component resolution, a rectangular window was used, since it possesses the lower central lobe.…”

Analysis of PSO, AIS and GA-based optimal Wavelet-Neural Network classifier in Brain–Robot Interface

“…are investigated [5,7,9,10]. In some other studies, Radial Basis function (RBF) kernelized SVM classifier is introduced as a powerful tool that has the highest performance accuracy among LDA, K-Nearest Neighbor (KNN), Quadratic Discriminant Analysis (QDA) and SVM [5,7]. Moreover, experimental results demonstrated that the performance of classification in terms of time and accuracy increases when unimportant features are neglected [7].…”

“…Furthermore, some other features such as standard deviation, variance and power of signals are used widely for EEG signals [6]. In the literature, reducing the number of features is considered by using Principal Component Analysis (PCA) or Independent Component Analysis (ICA) [7,8]. However there is no need for feature reduction methods when wavelet transform is used because it produces optimal quantity of information.…”

“…Performance of BRI mostly depends on classification algorithm. In last studies, different types of classifiers such as Support Vector Machine (SVM) [5,8], Linear Vector Quantization (LVQ) [5,7], Linear Discriminant Analysis (LDA) [5,8], different kinds of neural network [5,9], etc. are investigated [5,7,9,10].…”

“…In last studies, different types of classifiers such as Support Vector Machine (SVM) [5,8], Linear Vector Quantization (LVQ) [5,7], Linear Discriminant Analysis (LDA) [5,8], different kinds of neural network [5,9], etc. are investigated [5,7,9,10]. In some other studies, Radial Basis function (RBF) kernelized SVM classifier is introduced as a powerful tool that has the highest performance accuracy among LDA, K-Nearest Neighbor (KNN), Quadratic Discriminant Analysis (QDA) and SVM [5,7].…”