Feature Extraction and Classification of Biosignals - Emotion Valence Detection from EEG Signals

In this work a valence recognition system based on electroencephalograms is presented. The performance of the system is evaluated for two settings: single subjects (intra-subject) and between subjects (inter-subject). The feature extraction is based on measures of relative energies computed in short time intervals and certain frequency bands. The feature extraction is performed either on signals averaged over an ensemble of trials or on single-trial response signals. The subsequent classification stage is based on an ensemble classifier, i. e. a random forest of tree classifiers. The classification is performed considering the ensemble average responses of all subjects (inter-subject) or considering the single-trial responses of single subjects (intra-subject). Applying a proper importance measure of the classifier, feature elimination has been used to identify the most relevant features of the decision making.

[1]  Ana Maria Tomé,et al.  Application of SVM-RFE on EEG signals for detecting the most relevant scalp regions linked to affective valence processing , 2013, Expert Syst. Appl..

[2]  Jonas K. Olofsson,et al.  Affective picture processing: An integrative review of ERP findings , 2008, Biological Psychology.

[3]  D BamidisPanagiotis,et al.  On the classification of emotional biosignals evoked while viewing affective pictures , 2010 .

[4]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[5]  Rafael A. Calvo,et al.  Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications , 2010, IEEE Transactions on Affective Computing.

[6]  J. Russell.  A circumplex model of affect. , 1980 .

[7]  M. Macas,et al.  Classification of the emotional states based on the EEG signal processing , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[8]  Jennifer Healey,et al.  Toward Machine Emotional Intelligence: Analysis of Affective Physiological State , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[10]  Charalampos Bratsas,et al.  On the Classification of Emotional Biosignals Evoked While Viewing Affective Pictures: An Integrated Data-Mining-Based Approach for Healthcare Applications , 2010, IEEE Transactions on Information Technology in Biomedicine.

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  M. Bradley,et al.  The International Affective Picture System (IAPS) in the study of emotion and attention. , 2007 .

[13]  P. Lang.  International affective picture system (IAPS) : affective ratings of pictures and instruction manual , 2005 .

[14]  Jason Williams,et al.  Emotion Recognition Using Bio-sensors: First Steps towards an Automatic System , 2004, ADS.

[15]  K. H. Kim,et al.  Emotion recognition system using short-term monitoring of physiological signals , 2004, Medical and Biological Engineering and Computing.

[16]  Tanja Schultz,et al.  Towards emotion recognition from electroencephalographic signals , 2009, 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops.

[17]  Panagiotis D. Bamidis,et al.  A Framework Combining Delta Event-Related Oscillations (EROs) and Synchronisation Effects (ERD/ERS) to Study Emotional Processing , 2009, Comput. Intell. Neurosci..