文献类型：期刊文献

英文题名：Operator functional state classification using least-square support vector machine based recursive feature elimination technique

作者：Yin, Zhong[1];Zhang, Jianhua[1]

机构：[1]E China Univ Sci & Technol, Dept Automat, Shanghai 200237, Peoples R China

年份：2014

卷号：113

期号：1

起止页码：101

外文期刊名：COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE

收录：;EI(收录号：20144500157280);WOS:【SSCI(收录号:WOS:000327180900009)，SCI-EXPANDED(收录号:WOS:000327180900009)】；

基金：The authors would like to thank the developers of the ACAMS software which was used in our experiments. The work reported in this paper was supported by the National Natural Science Foundation of China under Grant No. 61075070 and Key Grant No. 11232005. This paper was completed when the first author (Z. Yin) was a visiting Ph.D student, funded by the China Scholarship Council (CSC), at the Control Systems Group (headed by Prof. Dr.-Ing. J. Raisch), Technical University of Berlin, whose support is sincerely appreciated. The authors acknowledge support of Shaozeng Yang for his comments and suggestions.

语种：英文

外文关键词：Operator functional state; Adaptive automation; Mental workload; Recursive feature elimination; Support vector machine

摘要：This paper proposed two psychophysiological-data-driven classification frameworks for operator functional states (OFS) assessment in safety-critical human-machine systems with stable generalization ability. The recursive feature elimination (RFE) and least square support vector machine (LSSVM) are combined and used for binary and multiclass feature selection. Besides typical binary LSSVM classifiers for two-class OFS assessment, two multiclass classifiers based on multiclass LSSVM-RFE and decision directed acyclic graph (DDAG) scheme are developed, one used for recognizing the high mental workload and fatigued state while the other for differentiating overloaded and base-line states from the normal states. Feature selection results have revealed that different dimensions of OFS can be characterized by specific set of psychophysiological features. Performance comparison studies show that reasonable high and stable classification accuracy of both classification frameworks can be achieved if the RFE procedure is properly implemented and utilized. (C) 2013 Elsevier Ireland Ltd. All rights reserved.