Log power representation of EEG spectral bands for the recognition of emotional states of mind

We present a new computational technique for obtaining effective spectral feature metrics from EEG data for the recognition of emotional states of mind. Sequences of 256 channel EEG data captured by applying appropriate stimuli patterns are analyzed to establish the spatiotemporal relationships of the signals for different emotional states. The signal sequence in each channel of the EEG data is decomposed into five specific spectral bands (delta, theta, alpha, beta and gamma bands) by a series of discrete wavelet transformations. Logarithmic compression of the spectral power values for each frequency band creates an effective set of features to represent different emotional states. The EEG data is preprocessed using a band-pass filter to remove frequency outliers, a notch filter to eliminate 60Hz line noise, and a surface Laplacian montage to reduce the effect of ocular artifacts. EEG data of five subjects for five different emotions were recorded by our dense array data acquisition system (Geodesic EEG System 300 from EGI, Inc.) with visual stimuli patterns from the International Affective Picture System. A trained multi-layer perceptron network based classifier is used to categorize the extracted feature sets to the respective emotional states of mind. It is experimentally observed that the new set of features could achieve 94.27% average recognition rate across five different emotions, which is a significant improvement over other state of the art feature representation methods.