Performance Improvement of Driving Fatigue Identification Based on Power Spectra and Connectivity Using Feature Level and Decision Level Fusions.

Abstract

Power and connectivity features extracted from EEG signals have been previously utilized to detect mental fatigue during driving. Although each of the feature categories has the discriminative power to differentiate alert and fatigue states, they might represent different aspects of information relevant to fatigue identification. Two fusion methods, feature level and decision level fusions, were proposed in this study to combine individual channel information (i.e., power features) and between-channel information (i.e., connectivity features). According to the results of the study, the average accuracies of the fusion methods were higher than the accuracies of the individual feature categories (feature level fusion: 84.70%, decision level fusion: 87.13%, power features: 80.82%, connectivity features: 79.36%). The statistical analysis demonstrated that the two fusion methods significantly improved the classification performance of driving fatigue. The fusion methods proposed in this study can be embedded into a driving fatigue detection system for a practical use in a vehicle.