Evaluation of mental fatigue using feature parameter extracted from event-related potential

Abstract

An attempt was made to evaluate mental fatigue induced during a VDT task using feature parameters extracted from an event-related potential (ERP) P300. Since the peak of the grand-averaged P300 waveform was not clear, it was sometimes difficult to detect the amplitude and the latency. The removal of the noisy electroencephalography (EEG) waveform based on the cross-correlation between a grand-averaged waveform and each waveform was found to be effective for making the P300 waveform clear. The parameter extraction methods using a principal component analysis and temporal changes of the cross-correlation function between the grand-averaged waveform and each waveform were used to evaluate mental fatigue. The P300b component and the standard deviation of the lime lag τ that corresponded to the maximum cross-correlation between the grand-averaged waveform and each EEG waveform were found to reflect some aspects of mental fatigue (the decreased function of cognitive information processing). Relevance to industry Fatigue, especially mental fatigue, is inevitable for office workers and in life in general. Fatigue is usually related to a loss of efficiency and disinclination to effort. It is important to manage and cope with fatigue so that the workers do not damage their health. It is also possible that cumulative mental fatigue leads to decreased productivity in the workplace and induces critical errors in the worst cases. Therefore, the management of mental fatigue is important from the viewpoint of occupational risk management, productivity, and occupational health. This study presents a systematic approach to the evaluation of mental fatigue induced during a VDT task. The proposed method provides a useful means for evaluating the state of mental fatigue, which would be potentially applicable to the management of fatigue from the three viewpoints listed above and would lead to increased agility in an organization.