AUTHOR=Chen Jing , Zhao Zexian , Shu Qinfen , Cai Guolong 

TITLE=Feature extraction based on microstate sequences for EEG–based emotion recognition

JOURNAL=Frontiers in Psychology

VOLUME=13

YEAR=2022

URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2022.1065196

DOI=10.3389/fpsyg.2022.1065196

ISSN=1664-1078

ABSTRACT=<p>Recognizing emotion from Electroencephalography (EEG) is a promising and valuable research issue in the field of affective brain-computer interfaces (aBCI). To improve the accuracy of emotion recognition, an emotional feature extraction method is proposed based on the temporal information in the EEG signal. This study adopts microstate analysis as a spatio-temporal analysis for EEG signals. Microstates are defined as a series of momentary quasi-stable scalp electric potential topographies. Brain electrical activity could be modeled as being composed of a time sequence of microstates. Microstate sequences provide an ideal macroscopic window for observing the temporal dynamics of spontaneous brain activity. To further analyze the fine structure of the microstate sequence, we propose a feature extraction method based on k-mer. K-mer is a k-length substring of a given sequence. It has been widely used in computational genomics and sequence analysis. We extract features that are based on the <inline-formula><mml:math id="M1" xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:msubsup><mml:mi>D</mml:mi><mml:mn>2</mml:mn><mml:mo>∗</mml:mo></mml:msubsup></mml:mrow></mml:math></inline-formula> statistic of k-mer. In addition, we also extract four parameters (duration, occurrence, time coverage, GEV) of each microstate class as features at the coarse level. We conducted experiments on the DEAP dataset to evaluate the performance of the proposed features. The experimental results demonstrate that the fusion of features in fine and coarse levels can effectively improve classification accuracy.</p>