文献类型：期刊文献

英文题名：Nonlinear Dynamic Classification of Momentary Mental Workload Using Physiological Features and NARX-Model-Based Least-Squares Support Vector Machines

作者：Zhang, Jianhua[1];Yin, Zhong[2];Wang, Rubin[3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Univ Shanghai Sci & Technol, Engn Res Ctr Opt Instrument & Syst, Minist Educ, Shanghai Key Lab Modern Opt Syst, Shanghai 200093, Peoples R China;[3]East China Univ Sci & Technol, Inst Cognit Neurodynam, Shanghai 200237, Peoples R China

年份：2017

卷号：47

期号：4

起止页码：536

外文期刊名：IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS

收录：;EI(收录号：20172203708513);WOS:【SSCI(收录号:WOS:000405732000010)，SCI-EXPANDED(收录号:WOS:000405732000010)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61075070 and Key Grant 11232005. This paper was recommended by Associate Editor V. Prasad. (Corresponding author: Jianhua Zhang.)

语种：英文

外文关键词：Dynamical systems; human-automation interaction; human factors; machine learning; mental workload (MWL); pattern classification

摘要：This paper designs a pattern classifier based on a Nonlinear AutoRegressive model with eXogenous inputs (NARX) to reveal intricate nonlinear dynamical correlation between mental workload (MWL) of a human operator and psychophysiological features. The salient electroencephalogram and electrocardiogram features were selected as inputs to the NARX model, whose continuous output was discretized in terms of five MWL classes at each time instant. The orders of the NARX model were determined using an objective function to achieve a good tradeoff between model accuracy and complexity via a least-squares support vector machine. The physiological features from different measurement channels (electrodes) and frequency bands were compared in terms of multiclass MWL classification performance. The classification results showed that the locality projection preservation technique can maintain sufficiently high MWL classification accuracy (with the highest five-class correct classification rate of 88%) with a significantly reduced computational complexity. The comparative results of classification performance also demonstrated the superiority of the proposed dynamic model to a widely-used static model.