Currently, driving state detection based on visual sensing has become the mainstream research direction for In-Cabin Sensing (ICS) technology. As a major contributor to traffic accidents, driving fatigue has increasingly received attention. The essence of driving fatigue detection is the indirect assessment process of the current driver’s state through the relevant features. In which, the calibration of fatigue states has significant impact for the establishment of feature-fatigue state mappings. Therefore, based on the electroencephalogram (EEG) data and the dynamic generation characteristic of driving fatigue, a Gaussian Mixture Hidden Markov Model (GM-HMM) for fatigue state assessment is proposed to provide certain references for the research of related on-board systems. Test results show that the proposed model is more superior than other related models in terms of accuracy, sensitivity and specificity.
Research of Driving Fatigue Detection Based on Gaussian Mixture Hidden Markov Model
Sae Technical Papers
3rd International Forum on Connected Automated Vehicle Highway System through the China Highway & Transportation Society ; 2020
2020-12-30
Conference paper
English
Research of Driving Fatigue Detection Based on Gaussian Mixture Hidden Markov Model
British Library Conference Proceedings | 2020
|Driving intention recognition method based on Gaussian mixture-hidden Markov model
European Patent Office | 2024
|Wheel Loader Driving Intention Recognition with Gaussian Mixture - Hidden Markov Model
DOAJ | 2018
|British Library Conference Proceedings | 2021
|