Enhancing Accuracy of Mental Fatigue Classification using Advanced Computational Intelligence in an Electroencephalography System

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
The 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014, pp. 1338 - 1341
Issue Date:
2014-01
Full metadata record
A system using electroencephalography (EEG) signals could enhance the detection of mental fatigue while driving a vehicle. This paper examines the classification between fatigue and alert states using an autoregressive (AR) model-based power spectral density (PSD) as the features extraction method and fuzzy particle swarm optimization with cross mutated of artificial neural network (FPSOCM-ANN) as the classification method. Using 32-EEG channels, results indicated an improved overall specificity from 76.99% to 82.02%, an improved sensitivity from 74.92 to 78.99% and an improved accuracy from 75.95% to 80.51% when compared to previous studies. The classification using fewer EEG channels, with eleven frontal sites resulted in 77.52% for specificity, 73.78% for sensitivity and 75.65% accuracy being achieved. For ergonomic reasons, the configuration with fewer EEG channels will enhance capacity to monitor fatigue as there is less set-up time required.
Please use this identifier to cite or link to this item: