用小波变换和神经网络来识别表面肌电信号的情感状态

Emotion recognition is a pivotal question of affective computing. This paper adopts the wavelet transform to analyse the surface EMG signal instability feature. Surface EMG signal is decomposed by discrete wavelet transform (DWT) and selected maximum and minimum of the wavelet coefficients in every level. The extracted maximum and minimum of the wavelet coefficients is inputted to identify emotion by the BP neural network improved by Levenberg-Marquardt algorithm. Experimental result shows that identification purpose of four emotional signals (joy, anger, sadness and pleasure) is effective and have are a great potential in practical application of emotion recognition.