文献类型：期刊文献

英文题名：Dynamical recursive feature elimination technique for neurophysiological signal-based emotion recognition

作者：Yin, Zhong[1];Liu, Lei[2];Liu, Li[1];Zhang, Jianhua[3];Wang, Yagang[1]

机构：[1]Univ Shanghai Sci & Technol, Shanghai Key Lab Modern Opt Syst, Minist Educ, Engn Res Ctr Opt Instrument & Syst, Jungong Rd 516, Shanghai 200093, Peoples R China;[2]Univ Shanghai Sci & Technol, Sch Management, Shanghai 200093, Peoples R China;[3]East China Univ Sci & Technol, Dept Automat, Shanghai 200237, Peoples R China

年份：2017

卷号：19

期号：4

起止页码：667

外文期刊名：COGNITION TECHNOLOGY & WORK

收录：;EI(收录号：20174604409129);WOS:【SSCI(收录号:WOS:000417269600009)，SCI-EXPANDED(收录号:WOS:000417269600009)】；

基金：This work was sponsored by The National Natural Science Foundation of China under Grant No. 61703277, The Shanghai Sailing Program (17YF1427000), The Shanghai Natural Science Fund (17ZR1419000), and The National Natural Science Foundation of China under Grant No. 61603256.

语种：英文

外文关键词：Emotion recognition; Affective computing; Physiological signals; Recursive feature elimination; EEG

摘要：The machine learning-based classification model can predict the operator emotional states in human-machine system based on nonlinear, multidimensional neurophysiological features. However, the dynamical properties of the testing physiological data regarding the time series may influence the feature distribution variation and inter-class discrimination across different time steps. To overcome this shortcoming, we propose a novel EEG feature selection method, dynamical recursive feature elimination (D-RFE), to find the optimal but different feature rankings at each time instant for arousal and valence recognition. With the classification framework implemented via a model-selected least square support vector machine, the participant-specific classification performance has been significantly improved against conventional RFE model and several common classifiers. The optimal classification accuracy and F1-score elicited by the proposed method are 0.7896, 0.7991, 0.7143, and 0.7257 for arousal and valence dimensions, respectively, which are quite competitive among recent reported works on the same EEG database.