This investigation assessed the impact of three cognitively demanding tasks on cognitive performance, subjective, and physiological indicators of mental fatigue. Following familiarization, participants completed four testing sessions, separated by 48 h. During each session, participants watched a 45-min emotionally neutral documentary (control) or completed one of the following computer tasks: Psychomotor Vigilance Task (PVT); AX-Continuous Performance Test (AX-CPT); or Stroop Task. Mental fatigue was assessed before and at regular periods for 60 min following the 45-min treatments. Cognitive performance was assessed using 3-min PVT, and task performance. Subjective assessments were conducted using the Brunel Mood Scale, and visual analog scales (VAS). Physiological indicators of mental fatigue included electroencephalography (EEG), and heart rate variability (HRV). Subjective ratings of mental fatigue increased from pre to 0-min post in all-treatments, but not the documentary (p < 0.05). Subjective fatigue (VAS) remained higher (p < 0.05) than pretreatment values for 20-, 50-, and 60-min following the PVT, Stroop, and AX-CPT respectively. The cognitively demanding tasks had unclear effects on 3-min PVT, EEG, and HRV assessments. Tasks requiring response inhibition appear to induce fatigue for longer durations than a simple vigilance task. Simple VAS appear to be the most practical method for assessing mental fatigue.

This paper presents a two-class electroencephal-ography-based classification for classifying of driver fatigue (fatigue state versus alert state) from 43 healthy participants. The system uses independent component by entropy rate bound minimization analysis (ERBM-ICA) for the source separation, autoregressive (AR) modeling for the features extraction, and Bayesian neural network for the classification algorithm. The classification results demonstrate a sensitivity of 89.7%, a specificity of 86.8%, and an accuracy of 88.2%. The combination of ERBM-ICA (source separator), AR (feature extractor), and Bayesian neural network (classifier) provides the best outcome with a p-value <; 0.05 with the highest value of area under the receiver operating curve (AUC-ROC = 0.93) against other methods such as power spectral density as feature extractor (AUC-ROC = 0.81). The results of this study suggest the method could be utilized effectively for a countermeasure device for driver fatigue identification and other adverse event applications.