文献类型：会议论文

英文题名：Performance Comparison of Machine Learning Algorithms for EEG-Signal-Based Emotion Recognition

作者：Chen, Peng[1];Zhang, Jianhua[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

会议论文集：26th International Conference on Artificial Neural Networks (ICANN)

会议日期：SEP 11-14, 2017

会议地点：Alghero, ITALY

语种：英文

外文关键词：Emotion recognition; Electroencephalogram (EEG); Nonlinear dynamics; Wavelet transform; Feature extraction; Dimensionality reduction

摘要：In this paper, we use the DEAP database to investigate emotion recognition problem. Firstly we use data clustering technique to determine four target classes of human emotional state. Then we compare two different feature extraction methods: one is wavelet transform and another is nonlinear dynamics. Furthermore, we examine the effect of feature reduction on classification performance. Finally, we compare the performance of four different classifiers, including k-nearest neighbor, naive Bayesian, support vector machine, and random forest. The results show the effectiveness of Kernel Spectral Regression (KSR) and random forest based classifier for emotion recognition and analysis.