Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (35): 216-218.

• 工程与应用 • Previous Articles     Next Articles

Emotion recognition of surface EMG signal based on wavelet transform

CHENG Bo1,LIU Guang-yuan2   

  1. 1.School of Computer and Information Science,Southwest University,Chongqing 400715,China
    2.School of Electronic and Information Engineering,Southwest University,Chongqing 400715,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-11 Published:2007-12-11
  • Contact: CHENG Bo

基于小波变换的表面肌电信号的情感识别

程 波1,刘光远2   

  1. 1.西南大学 计算机与信息科学学院,重庆 400715
    2.西南大学 电子信息工程学院,重庆 400715
  • 通讯作者: 程 波

Abstract: 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 joy,anger,sadness and pleasure four emotional signals is effective and have are a great potential in practical application of emotion recognition.

Key words: affective computing, emotion recognition, wavelet transform, BP neural network, EMG

摘要: 情感识别是情感计算的一个关键问题。针对表面肌电信号(EMG)的非平稳性,采用小波变换方法对表面肌电信号进行分析,提取小波系数最大值和最小值构造特征矢量输入用L-M算法改进的BP神经网络分类器进行情感状态识别。实验表明,用表面肌电信号对joy、anger、sadness、pleasure 4种情感识别效果较好。也说明用小波变换方法提取特征,用神经网络作分类器的方法用于情感识别有很大的应用前景。

关键词: 情感计算, 情感识别, 小波变换, BP网络, EMG