Title :
Emotion feature selection from physiological signals using tabu search
Author :
Yujing Wang ; Jianlin Mo
Author_Institution :
Dept. of Inf. Technol.2, Tianfu Coll. of SWUFE, Mianyang, China
Abstract :
A method of feature selection based on tabu search is proposed for recognizing affective states (joy, anger, sadness, pleasure). After combining with knear neighbour classifier, the tabu search heuristic algorithm achieved good recognition performance in the affective states classification , obtained the robust feature subsets which belong to 4 physiological signals (ECG, EMG, SC, RSP). Simulation showed that it is feasible and effective to recognize emotion using tabu search algorithm.
Keywords :
emotion recognition; pattern classification; search problems; ECG; EMG; RSP; SC; emotion feature selection; emotion recognition; k-near neighbour classifier; physiological signals; robust feature subsets; state classification; state recognition; tabu search heuristic algorithm; Educational institutions; Electrocardiography; Electromyography; Emotion recognition; Feature extraction; Physiology; Robustness; Emotion feature Recognition; Feature Selection; Physiological Signals; Tabu Search;
Conference_Titel :
Control and Decision Conference (CCDC), 2013 25th Chinese
Conference_Location :
Guiyang
Print_ISBN :
978-1-4673-5533-9
DOI :
10.1109/CCDC.2013.6561487
