摘要
针对基于生理信号的情感识别问题,采用具有模拟退火机制的遗传算法、最大最小蚁群算法和粒子群算法来进行特征选择,用Fisher分类器对高兴、惊奇、厌恶、悲伤、愤怒和恐惧6种情感进行分类,获得了较高的识别率,并找出了对情感识别系统模型的构建具有较好性能的特征组合,建立了对6类情感具有预测能力的识别系统。
For the problem of emotion recognition,genetic algorithm based on simulated-annealing method,max-min ant colony algorithm and particle swarm algorithm were used for feature selection,and combined with Fisher linear classifier to recognize six emotions:joy,surprise,disgust,grief,anger and fear,it has obtained higher recognition rate.Effective feature subset which can identify the emotion recognition system model with better performance was found,and the reco-gnition system was established with forecasting ability of six emotions.
出处
《计算机科学》
CSCD
北大核心
2011年第3期266-268,278,共4页
Computer Science
基金
国家自然科学基金(60873143)
西南大学国家重点学科基础心理学科研基金(NKSF07003)资助
关键词
情感识别
特征选择
智能算法
Emotion recognition
Feature selection
Intelligent algorithm