Table 10 Summary of studies on the recognition of fatigue using physiological signals.

Zhang et al.⁵⁵

ECG, waveforms

SVM (90%)

Patel et al.⁵⁶

HRV, linear parameters

Neural network (90%)

Awais et al.⁵⁷

EEG, ECG, linear and nonlinear

SVM (80.9%)

Zhang et al.⁵⁸

EEG, EMG, EOG, entropy, ROC curve

Artificial neural network (96.5%)

Anthony et al.³²

steering angle, pedal input, vehicle speed and acceleration, ROC curve (AUC)

DBN (0.72 (AUC))

Yuan et al.⁴⁵

EM, EEG, contextual

DBN

Yang et al.³⁰

Task performance

DBN

Ji et al.²⁷

Environmental factors, Eye closure, head movement, facial expressions

Bayesian network

Yang et al.²⁹

Environmental factors, Eye closure, head movement, facial expressions, EEG, Heart rate measures

DBN

Ji et al.²⁸

Environmental factors, Eye closure, head movement, facial expressions

DBN

Fu et al.¹³

EEG, EMG, various physiological and contextual information

DBN

This work

ECG, EMG, EM, GRA, contextual

DBN (0.971(r) )