Performance Analysis of Feature Extractors for Object Recognition from EEG Signals

Abstract

Recognition of objects from EEG signals requires selection of appropriate feature extraction and classification techniques with best efficiency in terms of highest classification accuracy with lowest run time for its applications in real time. The objective of this paper is to analyze the performance of various feature extraction techniques and to choose that particular method which can be implemented in real time system with best efficiency. The EEG signals are acquired from subjects while they explored the objects visually and visuo-tactually. Thus acquired EEG signals are preprocessed followed by feature extraction using adaptive autoregressive (AAR) parameters, ensemble empirical mode decomposition (EEMD), approximate entropy (ApEn) and multi-fractal detrended fluctuation analysis (MFDFA). The performance of these features are analyzed in terms of their dimension, extraction time and also depending upon the classification results produced by three classifiers [Support Vector machine (SVM), Naive Bayesian (NB), and Adaboost (Ada)] independently according to classification accuracy, sensitivity and classification times. The experimental results show that AAR parameter has an optimum dimension of 36 (not too large like EEMD i.e. 7,680 or too small like ApEn i.e. 6) and required minimum extraction as well as classification time of 0.59 and 0.008 s respectively. AAR also yielded highest maximum classification accuracy and sensitivity of 80.95 and 92.31 % respectively with NB classifier. Thus AAR parameters can be chosen for real time object recognition from EEG signal along with Naive Bayesian classifier.