文献类型：期刊文献

英文题名：Cross-Subject EEG Feature Selection for Emotion Recognition Using Transfer Recursive Feature Elimination

作者：Yin, Zhong[1];Wang, Yongxiong[1];Liu, Li[1];Zhang, Wei[1];Zhang, Jianhua[2]

机构：[1]Univ Shanghai Sci & Technol, Shanghai Key Lab Modern Opt Syst, Engn Res Ctr Opt Instrument & Syst, Minist Educ, Shanghai, Peoples R China;[2]East China Univ Sci & Technol, Dept Automat, Shanghai, Peoples R China

年份：2017

卷号：11

期号：APR

外文期刊名：FRONTIERS IN NEUROROBOTICS

收录：;EI(收录号：20171903649750);WOS:【SCI-EXPANDED(收录号:WOS:000399142100001)】；

基金：This work is sponsored by the Shanghai Sailing Program (17YF1427000), the National Natural Science Foundation of China under Grant No. 61673276, No. 11502145, No. 61603256. We thank all reviewers for their helpful comments and constructive suggestions on an earlier draft of this paper.

语种：英文

外文关键词：emotion recognition; affective computing; physiological signals; recursive feature elimination; EEG

摘要：Using machine-learning methodologies to analyze EEG signals becomes increasingly attractive for recognizing human emotions because of the objectivity of physiological data and the capability of the learning principles on modeling emotion classifiers from heterogeneous features. However, the conventional subject-specific classifiers may induce additional burdens to each subject for preparing multiple-session EEG data as training sets. To this end, we developed a new EEG feature selection approach, transfer recursive feature elimination (T-RFE), to determine a set of the most robust EEG indicators with stable geometrical distribution across a group of training subjects and a specific testing subject. A validating set is introduced to independently determine the optimal hyper-parameter and the feature ranking of the T-RFE model aiming at controlling the overfitting. The effectiveness of the T-RFE algorithmfor such cross-subject emotion classification paradigmhas been validated by DEAP database. With a linear least square support vector machine classifier implemented, the performance of the T-RFE is compared against several conventional feature selection schemes and the statistical significant improvement has been found. The classification rate and F-score achieve 0.7867, 0.7526, 0.7875, and 0.8077 for arousal and valence dimensions, respectively, and outperform several recent reported works on the same database. In the end, the T-RFE based classifier is compared against two subject-generic classifiers in the literature. The investigation of the computational time for all classifiers indicates the accuracy improvement of the T-RFE is at the cost of the longer training time.