Study on Driving Fatigue Evaluation System Based on Short Time Period ECG Signal

Fatigue driving is one of the most important causes of traffic accidents. Real-time fatigue driving detection and early warning is very important to reduce the number of traffic accidents, injuries, and deaths. Although traditional ECG (Electrocardiography) based methods can effectively identify fatigue state, they need a relatively long time period (in general 5 min) signal and can not be used to monitor fatigue state in real-time. In this paper, a short-time period ECG signals oriented method is proposed to improve detection real-time character. A pre-processing scheme is present to enhance the identifiably and frequency resolution of ECG signal. Meanwhile, a support vector machine (SVM) based fatigue detection model is given. Test results demonstrate that proposed method can effectively identify fatigue with only 5s interval ECG signal.