计算机科学 ›› 2012, Vol. 39 ›› Issue (3): 212-215.
• 人工智能 • 上一篇 下一篇
曹军,刘光远,赖祥伟
出版日期:
发布日期:
CAO Jun,LIU Guam-yuan,LAI Xiang-wei
Online:
Published:
摘要: 针对心电(ECG)信号情感识别中特征选择的问题,首先运用相关性分析方法,去除原始特征集中的高相关度 特征,实现原始特征集的降维;其次,为了在降维后的特征空间中进行有效的特征选择,提出了一种改进的二进制量子 粒子群算法(CSBQPSO)。实验结果表明,基于本算法结合Fisher分类器建立的ECU信号情感识别系统能够对高兴、 惊奇、厌恶、悲伤、愤怒和恐惧6种情感达到良好的识别效果。
关键词: 特征选择,相关性分析,二进制量子粒子群算法,情感识别
Abstract: This paper discussed the feature selection from ECG signal in affective recognition. At first, the original fcatures with high correlation were deleted to reduce dimensionality of original feature set by correlation analysis. Andthen, an improved quantum-behaved particle swarm optimization with binary encoding algorithm was proposed to achieve effective feature selection in the feature space with reduced dimension. hhe experimental results shows that the affective recognition system based on this algorithm and fisher classifier recognize the anger,disgust,fear,grief,joy and surpnse successfully.
Key words: Feature selection, Correlation analysis, I3QPS0 algorithm, Affective recognition
曹军,刘光远,赖祥伟. 量子粒子群和相关性分析在心电特征选择中的应用[J]. 计算机科学, 2012, 39(3): 212-215. https://doi.org/
CAO Jun,LIU Guam-yuan,LAI Xiang-wei. Application of QPSO Algorithm and Correlation Analysis in Feature Selection from ECG Signal[J]. Computer Science, 2012, 39(3): 212-215. https://doi.org/
0 / / 推荐
导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks
链接本文: https://www.jsjkx.com/CN/
https://www.jsjkx.com/CN/Y2012/V39/I3/212
Cited