Distinguishing two Different Mental States with Application of Non-Linear Parameters

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 analyse EEG signal. EMD is a mathematical technique which is suitable to analyze a non-stationary and non-linear 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 four different features obtained from the 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. Two well-known multi-variate 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