基于TS特征选择的生理情感状态分类

Emotion of physiological signals classification based on TS feature selection

针对生理信号的情感识别问题,本文提出了禁忌搜索(TS)和神经网络结合的情感状态分类方法。该方法用禁忌搜索算法选择情感生理信号特征,神经网络BP算法分类情感状态。仿真实验结果表明,BP分类器在TS选择的特征基础上达到很好的情感分类效果。

This paper propose a method of TS-MLP about emotion recognition of physiological signal . It can recognize emotion successfully by Tabu search which selects features of emotion＇ s physiological signals and Muhilayer Perceptron that is used to classify emotion. Simulation shows that it has achieved good emotion classification performance.