基于小波变换的表面肌电信号的情感识别

Emotion recognition is a pivotal question of Affective Computing. I analyze surface EMG signal with adopting the wavelet transform for instability of surface EMG signal and extract maximum and minimum of the wavelet coefficients to identify emotion with L-M arithmetic mended back propagation artificial neural network. Experimental result shows that identification purpose of joy anger sadness and pleasure four emotional signals is preferable and this method has a great potential in practical application of emotion recognition.