Non-contact Fatigue Driving Detection Using CW Doppler Radar

This paper presents a non-contact fatigue driving monitoring method using the continuous-wave (CW) Doppler radar. The driver's breathing and heartbeat signals can be measured by the Doppler radar located at the car instrument panel. Then seven features in the time-domain and frequency-domain are extracted from the received signal. Extensive experiments are conducted to collect 240 observations from three healthy volunteers. Finally, a decision tree based on detection algorithm is realized to achieve the accuracy rate of 82.5%, which demonstrates the feasibility of the proposed method for fatigue driving monitoring.

[1]  Xiaohua Zhu,et al.  Doppler radar-based human breathing patterns classification using Support Vector Machine , 2017, 2017 IEEE Radar Conference (RadarConf).

[2]  Zhu Xue-feng.  The Research Development on Driving Fatigue Based on PERCLOS , 2008 .

[3]  Wei Sun,et al.  A Real-Time Fatigue Driving Recognition Method Incorporating Contextual Features and Two Fusion Levels , 2017, IEEE Transactions on Intelligent Transportation Systems.

[4]  Shashwat Jain,et al.  Handwritten digit recognition using hoeffding tree, decision tree and random forests — A comparative approach , 2017, 2017 International Conference on Computational Intelligence in Data Science(ICCIDS).

[5]  P. Eiffert.  Guidelines for the Economic Evaluation of Building-Integrated Photovoltaic Power Systems , 2003 .

[6]  Masatomo Kobayashi,et al.  Fatigue Detection Model for Older Adults Using Eye-Tracking Data Gathered While Watching Video: Evaluation Against Diverse Fatiguing Tasks , 2017, 2017 IEEE International Conference on Healthcare Informatics (ICHI).

[7]  Xun Zhang,et al.  Traffic accidents involving fatigue driving and their extent of casualties. , 2016, Accident; analysis and prevention.

[8]  Cheng Zhang,et al.  An EEG-based method for detecting drowsy driving state , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[9]  A. Singh,et al.  Driver fatigue detection using machine vision approach , 2013, 2013 3rd IEEE International Advance Computing Conference (IACC).

[10]  Kai Keng Ang,et al.  Correlation of reaction time and EEG log bandpower from dry frontal electrodes in a passive fatigue driving simulation experiment. , 2017, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.