Automatic detection of alertness/drowsiness from physiological signals using wavelet-based nonlinear features and machine learning

作者：

Highlights：

• A drowsiness detection system based on EEGs and eyelid movements is proposed.

• Nonlinear features are extracted and fused from EEG wavelet sub-bands.

• An efficient detector “extremely learning machine” is employed.

• The proposed method achieves high detection accuracy and fast computation speed.

摘要

•A drowsiness detection system based on EEGs and eyelid movements is proposed.•Nonlinear features are extracted and fused from EEG wavelet sub-bands.•An efficient detector “extremely learning machine” is employed.•The proposed method achieves high detection accuracy and fast computation speed.

论文关键词：Drowsiness detection,Electroencephalogram (EEG),Eyelid movements,Wavelet decomposition,Nonlinear features,Extreme learning machine (ELM)

论文评审过程：Available online 24 May 2015, Version of Record 17 June 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.05.028