Fangjie Song

A variety of technologies that could enhance driving safety are being actively explored, with the aim of reducing traffic accidents by accurately recognizing the driver’s state. In this field, three mainstream detection methods have been widely applied, namely visual monitoring, physiological indicator monitoring and vehicle behavior analysis. In order to achieve more accurate driver state recognition, we adopted a multi-sensor fusion approach. We monitored driver physiological signals, electroencephalogram (EEG) signals and electrocardiogram (ECG) signals to determine fatigue state, while an in-vehicle camera observed driver behavior and provided more information for driver state assessment. In addition, an outside camera was used to monitor vehicle position to determine whether there were any driving deviations due to distraction or fatigue. After a series of experimental validations, our research results showed that our multi-sensor approach exhibited good performance for driver state recognition. This study could provide a solid foundation and development direction for future in-depth driver state recognition research, which is expected to further improve road safety.

Stress usually causes changes in the status of the primary and secondary sympathetic nerves of the autonomic nervous system. This is also reflected in changes in indicators related to heart rate variability. Therefore, stress identification through the characteristics of heart rate variability is very effective. In this paper, Electrocardiographic Stress Detection (ESD) model based on heart rate variability is proposed to accurately identify stress from an objective perspective using physiological signals. Among them, the heart rate variability (HRV) in the ECG signal is the main feature involved in the ESD model, which is related to the response pattern of the human autonomic nervous system, and the changes of the relevant features represent the active state of the main sympathetic and parasympathetic nerves. Based on these patterns, we extracted the relevant HRV features and used a support vector machine (SVM) classifier for classification calculations with an accuracy of 94.8%.