| 改进的禁忌搜索算法在肌电信号情感识别中的应用 |
| |
| 引用本文： | 邱红,刘光远,赖祥伟.改进的禁忌搜索算法在肌电信号情感识别中的应用[J].计算机工程与设计,2012,33(4):1553-1557. |
| |
| 作者姓名： | 邱红 刘光远 赖祥伟 |
| |
| 作者单位： | 1. 西南大学电子信息工程学院,重庆,400715
2. 西南大学计算机与信息科学学院,重庆,400715 |
| |
| 基金项目： | 国家自然科学基金项目(60873143);国家重点学科基础心理学科研基金项目(NKFS07003);中央高校基本科研业务费专项基金项目(XDJK2009B008);教育部科学技术研究重大基金项目(311012) |
| |
| 摘 要： | 针对基于肌电(EMG)信号的情感识别问题,提出了一种新颖的特征选择方法.该方法用相关性分析对原始特征降维,再利用改进的禁忌搜索算法结合Fisher分类器,对高兴、厌恶、悲伤、惊奇、愤怒和恐惧6种肌电信号的情感进行特征选择.实验结果表明,该方法能以较少的特征获得较高的识别率,得到了有利于情感识别系统建立的有效特征子集.
|
| 关 键 词： | 特征选择 情感识别 肌电信号 禁忌搜索算法 相关性分析 |
Application of improved tabu search algorithm in affective recognition from EMG signal |
| |
| QIU Hong
,
LIU Guang-yuan
,
LAI Xiang-wei.Application of improved tabu search algorithm in affective recognition from EMG signal[J].Computer Engineering and Design,2012,33(4):1553-1557. |
| |
| Authors: | QIU Hong LIU Guang-yuan LAI Xiang-wei |
| |
| Affiliation: | 1.School of Electronics and Information Engineering,Southwest University,Chongqing 400715,China; 2.School of Computer and Information Science,Southwest University,Chongqing 400715,China) |
| |
| Abstract: | To solve electromyography(EMG)-based affective recognition problem effectively,a novel feature selection method is proposed.First,correlation analysis is used to reduce the dimension of original feature subset.Then improved tabu search algorithm combined with Fisher classifier is adopted to find six electromyography(EMG) emotions(joy,disgust,grief,surprise,anger and fear) feature selection.The experimental results show that the method can obtain relatively high recognition rates with fewer features,and effective feature subsets beneficial to the establishment of affective recognition system are obtained. |
| |
| Keywords: | feature selection affective recognition EMG signal tabu search algorithm correlation analysis |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
