文献类型：期刊文献

英文题名：Instantaneous mental workload assessment using time-frequency analysis and semi-supervised learning

作者：Zhang, Jianhua[1];Li, Jianrong[2];Wang, Rubin[3]

机构：[1]Oslo Metropolitan Univ, Dept Comp Sci, AI Lab, N-0166 Oslo, Norway;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[3]East China Univ Sci & Technol, Sch Sci, Inst Cognit Neurodynam, Shanghai 200237, Peoples R China

年份：2020

卷号：14

期号：5

起止页码：619

外文期刊名：COGNITIVE NEURODYNAMICS

收录：;WOS:【SSCI(收录号:WOS:000532156100001)，SCI-EXPANDED(收录号:WOS:000532156100001)】；

基金：Open Access funding provided by OsloMet - Oslo Metropolitan University. This work was supported in part by the OsloMet Faculty TKD Lighthouse Project No. 201369-100. The first author (J. Zhang) would like to thank Dr. Stefano Nichele for stimulating discussions.

语种：英文

外文关键词：Mental workload; Operator functional state; Physiological signals; Time-frequency analysis; Semi-supervised learning

摘要：The real-time assessment of mental workload (MWL) is critical for development of intelligent human-machine cooperative systems in various safety-critical applications. Although data-driven machine learning (ML) approach has shown promise in MWL recognition, there is still difficulty in acquiring a sufficient number of labeled data to train the ML models. This paper proposes a semi-supervised extreme learning machine (SS-ELM) algorithm for MWL pattern classification requiring only a small number of labeled data. The measured data analysis results show that the proposed SS-ELM paradigm can effectively improve the accuracy and efficiency of MWL classification and thus provide a competitive ML approach to utilizing a large number of unlabeled data which are available in many real-world applications.