Using Support Vector Regression to estimate valence level from EEG

Emotion recognition is an integral part of affective computing. An affective brain-computer-interface (BCI) can benefit the user in a number of applications. In most existing studies, EEG (electroencephalograph)-based emotion recognition is explored in a classificatory manner. In this manner, human emotions are discretized by a set of emotion labels. However, human emotions are more of a continuous phenomenon than discrete. A regressive approach is more suited for continuous emotion recognition. Few studies have looked into a regressive approach. In this study, we investigate a portfolio of EEG features including fractal dimension, statistics and band power. Support vector regression (SVR) is employed in this study to estimate subject's valence level by means of different features under two evaluation schemes. In the first scheme, a SVR is constructed with full training resources, whereas in the second scheme, a SVR only receives minimal training resources. MAE (mean absolute error) averages of 0.74 and 1.45 can be achieved under the first and the second scheme, respectively, by fractal feature. The advantages of a regressive approach over classificatory approach lie in continuous emotion recognition and the possibility to reduce training resources to minimal level.

[1]  Ian Daly,et al.  Neural correlates of emotional responses to music: An EEG study , 2014, Neuroscience Letters.

[2]  Laurel J. Trainor,et al.  Processing Emotions Induced by Music , 2003 .

[3]  Yuan-Pin Lin,et al.  EEG-based emotion recognition in music listening: A comparison of schemes for multiclass support vector machine , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  A. Mehrabian.  Pleasure-arousal-dominance: A general framework for describing and measuring individual differences in Temperament , 1996 .

[5]  Thierry Pun,et al.  DEAP: A Database for Emotion Analysis ;Using Physiological Signals , 2012, IEEE Transactions on Affective Computing.

[6]  Masafumi Hagiwara,et al.  A feeling estimation system using a simple electroencephalograph , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

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

[8]  Olga Sourina,et al.  Real-Time EEG-Based Human Emotion Recognition and Visualization , 2010, 2010 International Conference on Cyberworlds.

[9]  R. Nagarajan,et al.  Combining Spatial Filtering and Wavelet Transform for Classifying Human Emotions Using EEG Signals , 2011 .

[10]  K. Stevens,et al.  Emotions and speech: some acoustical correlates. , 1972, The Journal of the Acoustical Society of America.

[11]  Qiang Wang,et al.  Fractal-Based Brain State Recognition from EEG in Human Computer Interaction , 2011, BIOSTEC.

[12]  L. Trainor,et al.  Frontal brain electrical activity (EEG) distinguishes valence and intensity of musical emotions , 2001 .

[13]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[14]  Yichen Wang,et al.  Detecting Emotions in Social Media: A Constrained Optimization Approach , 2015, IJCAI.

[15]  E. Vesterinen,et al.  Affective Computing , 2009, Encyclopedia of Biometrics.

[16]  Turhan Canli,et al.  Individual differences in emotion processing , 2004, Current Opinion in Neurobiology.

[17]  B. Efron.  Better Bootstrap Confidence Intervals , 1987 .

[18]  Bao-Liang Lu,et al.  EEG-Based Emotion Recognition Using Frequency Domain Features and Support Vector Machines , 2011, ICONIP.

[19]  Qiang Ji,et al.  Facial Action Unit Recognition by Exploiting Their Dynamic and Semantic Relationships , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Mohammad Soleymani,et al.  Continuous emotion detection in response to music videos , 2011, Face and Gesture 2011.

[21]  Serdar Yildirim,et al.  Emotion primitives estimation from EEG signals using Hilbert Huang Transform , 2012, Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics.

[22]  Olga Sourina,et al.  Real-Time EEG-Based Emotion Recognition and Its Applications , 2011, Trans. Comput. Sci..