Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (26): 214-216.DOI: 10.3778/j.issn.1002-8331.2008.26.065

• 工程与应用 • Previous Articles     Next Articles

Emotion recognition based on wavelet packet entropy of surface EMG signal

CHENG Bo1,LIU Guang-yuan2   

  1. 1.School of Economics and Management,Chongqing Three Gorges University,Chongqing 404000,China
    2.School of Electronic and Information Engineering,Southwest University,Chongqing 400715,China
  • Received:2007-09-25 Revised:2007-11-30 Online:2008-09-11 Published:2008-09-11
  • Contact: CHENG Bo

基于表面肌电信号小波包熵的情感识别

程 波1,刘光远2   

  1. 1.重庆三峡学院 经济与管理学院,重庆 404000
    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 classifies surface EMG signal with adopting the wavelet packet entropy for instability of surface EMG signal.Experimental result shows that identification purpose of two kinds of emotion with high arousal and low arousal combined is preferable make use of wavelet packet entropy.

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,根据小波包变换在不同时频段均能精确的刻画信号,并提供丰富模式信息的特点,提出利用小波包熵方法对不同情感状态下的表面肌电信号进行分析。实验表明,该方法对情感的唤醒度识别效果较好。