A Novel Approach of Emotion Recognition based on Selective Ensemble

摘要：

Emotion recognition is an important module inaffective computing.It is usually studied based onfacial and audio information with methodologies suchas ANN,fuzzy set,SVM,HMM,etc.In this paper,anovel approach based on selective ensemble isproposed for emotion recognition. Simulationexperiments prove that the proposed method has betterperformance than the method of single classifier,evenbetter than bagging.In the end,further research worksis discussed.

关键词： Affective computing emotion recognition support vector machine ensemble learning selective ensemble.

作者: Zhenguo Zhu Kun He

作者单位: School of Computer and Information,Chongqing Jiaotong University,Chongqing,400074,.China Institute of Computer Science &Technology,Chongqing University of Posts and Telecommunications,Chong

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 695-698

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）