Research on mental load state recognition based on combined information sources. (February 2023)

• Record Type: Journal Article
• Authors: Wang, Huiyu; Zheng, Xin; Hao, Tengteng; Yu, Yanwu; Xu, Kaili; Wang, Yicheng
• Is Part Of: Biomedical signal processing and control. Volume 80:Part 2(2023)
• Publication Date: 2023-02
• Subjects: Mental load assessment -- EEG -- Eye movements -- Machine learning; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104341
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The patterns of changes in EEG and eye movement indicators in people under stressful and high-risk situations were studied. A combination of subjective and objective methods was used to determine whether participants developed mental load. The variables including physiological indicators optimized by Relief are used in classifier to find the best result. Mental load affects the characteristics of each brain region differently, and eye movement also proved to be highly feasible. Abstract: Whether from a theoretical research perspective or a practical situation, mental loads lead to lower productivity, worse job quality, and industrial accidents, and evaluating the mental loads of workers is important for task assignment, job performance, and production safety. In this study, impact sensitivity experiments were used to induce emotions such as fear and tension in participants, thus causing them to develop mental load. Prospective time-distance estimation tests and subjective questionnaires were used to validate the induction experiment. EEG signals from three brain regions and eye movements of the subjects made up four single variables, and combinations of different brain regions and eye movements were used as combined variables. Thus, a total of 15 variables were used for the analysis of mental load states. The Relief algorithm was applied to the 15 variables for feature extraction to construct an optimized feature set. Then, 4 types of classifiers were used to identify mental load states. The combination of occipital area and eye movement variables achieved better mental load assessment results than single variables. With this combination variable, the SVM (94.9 %) and RF (94.3 %) classifiers were effective. However, the SVM classification accuracy gradually increased with the number of training sessions, while the RF classifier did not show this trend. Therefore, the SVM classifier was the best mental load classification method. The results of this study can be used to assess the mental loads of workers, reducing the number of accidents and improving productivity.