Teager energy operated perceptual wavelet packet transform coefficients for arithmetic task classification from EEG signals

Recently the development of brain-computer interface applications has drawn the attention of research community as it can assist physically challenged people to communicate with their brain electroencephalogram (EEG) signal. In this paper, a Brain-Computer Interface (BCI) is designed using electroencephalogram (EEG) signals where the subjects have to think of only a single mental task. The presented BCI approach includes three stages: (a) filtering out the electrical frequency components and segmentation of the raw signals (b) Perceptual wavelet packet transform of the segments and calculating the Teager Energy(TE) of the subbands (c) classification using SVM classifier. Perceptual wavelet packet transform is used to decompose the EEG signals into a number of frequency bands, and Teager Energy is calculated to maintain distinguishable energy profiles of those bands which provide a maximum classification accuracy of about 100%.