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.

[1]  D J McFarland,et al.  An EEG-based brain-computer interface for cursor control. , 1991, Electroencephalography and clinical neurophysiology.

[2]  M A Kulikov,et al.  Frequency characteristics of EEG spectra in the emotions. , 1996, Neuroscience and behavioral physiology.

[3]  M. Bradley,et al.  Emotion and motivation I: defensive and appetitive reactions in picture processing. , 2001, Emotion.

[4]  J. J. Wright,et al.  Autoregression models of EEG , 2004, Biological Cybernetics.

[5]  M. Akin,et al.  Comparison of Wavelet Transform and FFT Methods in the Analysis of EEG Signals , 2002, Journal of Medical Systems.

[6]  Nurettin Acir,et al.  Automatic recognition of sleep spindles in EEG via radial basis support vector machine based on a modified feature selection algorithm , 2004, Neural Computing & Applications.

[7]  Paul L. Nunez,et al.  The surface laplacian, high resolution EEG and controversies , 2005, Brain Topography.

[8]  Philippe Renevey,et al.  SVM-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband EEG signals in Brain-Computer Interfaces , 2005, Signal Process..

[9]  Emanuel Donchin,et al.  A P 300-based brain – computer interface : Initial tests by ALS patients Eric , 2006 .

[10]  Abdulhamit Subasi,et al.  EEG signal classification using wavelet feature extraction and a mixture of expert model , 2007, Expert Syst. Appl..

[11]  Zhiqiang Cheng,et al.  Wavelet Transform and Singular Value Decomposition of EEG Signal for Pattern Recognition of Complicated Hand Activities , 2007, HCI.

[12]  Vijayan K. Asari,et al.  Brain Signal Analysis for the Classification of Mental States , 2007 .

[13]  Andrzej Cichocki,et al.  Emotional States Estimation from Multichannel EEG Maps , 2008 .

[14]  Yaacob Sazali,et al.  Classification of human emotion from EEG using discrete wavelet transform , 2010 .

[15]  Kemal Polat,et al.  Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting , 2010, Expert Syst. Appl..