International Journal of Man-Machine Studies
Affective computing
Rough set approach to incomplete information systems
Information Sciences: an International Journal
Rules in incomplete information systems
Information Sciences: an International Journal
Toward Machine Emotional Intelligence: Analysis of Affective Physiological State
IEEE Transactions on Pattern Analysis and Machine Intelligence - Graph Algorithms and Computer Vision
Affective computing: challenges
International Journal of Human-Computer Studies - Application of affective computing in humanComputer interaction
An Emotion Recognition System Based on Rough Set Theory
Proceedings of the 2006 conference on Advances in Intelligent IT: Active Media Technology 2006
Feature selection in audiovisual emotion recognition based on rough set theory
Transactions on rough sets VII
Domain-oriented data-driven data mining (3DM): simulation of human knowledge understanding
WImBI'06 Proceedings of the 1st WICI international conference on Web intelligence meets brain informatics
Facial expression recognition based on rough set theory and SVM
RSKT'06 Proceedings of the First international conference on Rough Sets and Knowledge Technology
Hi-index | 0.00 |
Affective computing is becoming a more and more important topic in intelligent computing technology. Emotion recognition is one of the most important topics in affective computing. It is always performed on face and voice information with such technology as ANN, fuzzy set, SVM, HMM, etc. In this paper, based on the idea of data driven data mining and rough set theory, a novel emotion recognition method is proposed. Firstly, an information system including facial features is taken as a tolerance relation in rough set, based on the idea of data driven data mining, a suitable threshold is selected for the tolerance relation. Then a reduction algorithm based on condition entropy is proposed for the tolerance relation, SVM is taken as the final classifier. Simulation experiment results show that the proposed method can use less features and get higher recognition rate, and the proposed method is proved effective and efficient.