Affection Recognition by GSR Signal Use a Improved K-nearest Neighbor Algorithm

For afiection recognition problems of GSR (Galvanic Skin Response) signal, this paper presents a method of afiection recognition based on a improved K-nearest neighbor algorithm. In this research, on the flrst step, the group collected 175 participants’ GSR signals on the test of emotional arousal which was acquired in the lab environment; then used the Batterworth low pass fllter to remove GSR signals noise, and extracted the original features of GSR signals at the same time; then recognized the flve feelings of happiness, sadness, fear, anger and calm with the improved K- nearest neighbor classifler. The experimental results show that the method can improves the accuracy of identiflcation indeed.

[1]  Changchun Liu,et al.  Interaction between human and robot An affect-inspired approach , 2008 .

[2]  Zhang Zuxun,et al.  Genetic feature selection for texture classification , 2004 .

[3]  Michail Zak.  Physical model of immune inspired computing , 2000, Inf. Sci..

[4]  Marco Dorigo,et al.  Ant colony optimization , 2006, IEEE Computational Intelligence Magazine.

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

[6]  Thierry Pun,et al.  Multimodal Emotion Recognition in Response to Videos , 2012, IEEE Transactions on Affective Computing.

[7]  Guanghua Wu,et al.  The Analysis of Emotion Recognition from GSR Based on PSO , 2010, 2010 International Symposium on Intelligence Information Processing and Trusted Computing.

[8]  Klaus R. Scherer,et al.  Advocating a Componential Appraisal Model to Guide Emotion Recognition , 2012, Int. J. Synth. Emot..

[9]  Shweta Taneja,et al.  An Enhanced K-Nearest Neighbor Algorithm Using Information Gain and Clustering , 2014, 2014 Fourth International Conference on Advanced Computing & Communication Technologies.

[10]  Ralf Hartmut Güting,et al.  Efficient k-nearest neighbor search on moving object trajectories , 2010, The VLDB Journal.

[11]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Fernando De la Torre,et al.  Optimal feature selection for support vector machines , 2010, Pattern Recognit..