首页 | 本学科首页   官方微博 | 高级检索  
     

基于小波变换与神经网络的表面肌电信号的情感识别
引用本文:程波,刘光远.基于小波变换与神经网络的表面肌电信号的情感识别[J].计算机应用,2008,28(2):333-335.
作者姓名:程波  刘光远
作者单位: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
摘    要:情感识别是情感计算的一个关键问题。针对表面肌电图(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,分别输入用L-M算法改进的BP神经网络分类器和最近邻法分类器进行情感识别。实验表明,提取EMG的小波系数对joy、anger、sadness、pleasure四种情感进行识别,BP神经网络分类器识别效果优于最近邻法分类器。说明小波变换的方法对EMG进行分析是可行且有效的,并有很大的应用前景。

关 键 词:情感识别  近邻法  小波变换  BP网络  EMG
文章编号:1001-9081(2008)02-0333-03
收稿时间:2007-08-31
修稿时间:2007-11-06

Emotion recognition from surface EMG signal using wavelet transform and neural network
CHENG Bo,LIU Guang-yuan.Emotion recognition from surface EMG signal using wavelet transform and neural network[J].journal of Computer Applications,2008,28(2):333-335.
Authors:CHENG Bo  LIU Guang-yuan
Affiliation:CHENG Bo1,LIU Guang-yuan2(1.School of Computer , Information Science,Southwest University,Chongqing 400715,China,2.School of Electronic , Information Engineering,China)
Abstract:Emotion recognition is critical in affective computing. This paper adopted the wavelet transform to analyse the surface EMG signal instability feature. Surface EMG signal was decomposed by discrete wavelet transform (DWT) and maximum and minimum of the wavelet coefficients in every level were extracted. The extracted maximum and minimum of the wavelet coefficients were input to identify emotion by the BP neural network improved by Levenberg-Marquardt algorithm. Experimental result shows that the identification of four emotional signals (joy, anger, sadness and pleasure) is effective and it has great potential in practical application of emotion recognition.
Keywords:Emotion Recognition  Nearest Neighbor method  Wavelet Transform  BP Neural Network  EMG
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号