EEG-based Emotion Recognition Using Self-Organizing Map for Boundary Detection

This paper presents an EEG-based emotion recognition system using self-organizing map for boundary detection. Features from EEG signals are classified by considering the subjects’ emotional responses using scores from SAM questionnaire. The selection of appropriate threshold levels for arousal and valence is critical to the performance of the recognition system. Therefore, this paper investigates the performance of a proposed EEG-based emotion recognition system that employed self-organizing map to identify the boundaries between separable regions. A study was performed to collect 8 channels of EEG data from 26 healthy right-handed subjects in experiencing 4 emotional states while exposed to audio-visual emotional stimuli. EEG features were extracted using the magnitude squared coherence of the EEG signals. The boundaries of the EEG features were then extracted using SOM. 5-fold cross-validation was then performed using the k-nn classifier. The results showed that proposed method improved the accuracies to 84.5%.

[1]  Tieniu Tan,et al.  Affective Computing: A Review , 2005, ACII.

[2]  I. Peretz,et al.  Happy, sad, scary and peaceful musical excerpts for research on emotions , 2008 .

[3]  William J. German,et al.  The Hypothalamus and Central Levels of Autonomic Function , 1940, Nature.

[4]  Herbert Gish.  The magnitude squared coherence estimate: A geometric view , 1984, ICASSP.

[5]  R. F. Farquharson.  The Hypothalamus and Central levels of Autonomic Function. Proceedings of the Association for Research in Nervous and Mental Disease, December 20 and 21, 1939, New York. Research Publications, Association for Research in Nervous and Mental Disease, Volume XX , 1942 .

[6]  L. Aftanas,et al.  Human anterior and frontal midline theta and lower alpha reflect emotionally positive state and internalized attention: high-resolution EEG investigation of meditation , 2001, Neuroscience Letters.

[7]  Benoit Huet,et al.  Bimodal Emotion Recognition , 2010, ICSR.

[8]  T. Dalgleish.  Basic Emotions , 2004 .

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

[10]  Kai Keng Ang,et al.  Affective computation on EEG correlates of emotion from musical and vocal stimuli , 2009, 2009 International Joint Conference on Neural Networks.

[11]  Mohammad Soleymani,et al.  Short-term emotion assessment in a recall paradigm , 2009, Int. J. Hum. Comput. Stud..

[12]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

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

[14]  Jonghwa Kim,et al.  Bimodal Emotion Recognition using Speech and Physiological Changes , 2007 .

[15]  Christine L. Lisetti,et al.  A User-Modeling Approach to Build User's Psycho-Physiological Maps of Emotions using Bio-Sensors , 2006, ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication.

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

[17]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[18]  G. Erdmann,et al.  Interaction between physiological and cognitive determinants of emotions: Experimental studies on Schachter's theory of emotions , 1978, Biological Psychology.

[19]  P. Lang.  Behavioral treatment and bio-behavioral assessment: computer applications , 1980 .