Drowsiness estimation under driving environment by heart rate variability and/or breathing rate variability with logistic regression analysis

It is widely known that many traffic accidents occur every year, not only in Japan but also in the world. Drowsiness or sleepiness, which is the cause of dozing at the wheel, happens regardless of the physical condition of the driver after having meals or during midnight. This means that to avoid driver´s drowsiness or sleepiness by oneself is hard. Therefore, various systems have been proposed to prevent traffic accidents caused by dozing at the wheel. In this study, we examined the relationship between psychological drowsiness during driving, which was evaluated by the Japanese version of the Karolinska sleepiness scale (KSS-J) and physiological parameters extracted from electrocardiogram and respiration signals. Then we tried to estimate the existence of drowsiness using logistic regression analysis on that parameters. In this study, since KSS-J score 7 indicates sleepy, we determined KSS-J score 7 and more as drowsiness state. The logistic regression method was performed using the half of the data for each subject and used the remaining data as the testing data. As a result, we got 71% of accuracy with heart rate variability (HRV), 72% of accuracy with breathing rate variability (BRV), 81% of accuracy with both signals in the whole subjects using logistic regression. Therefore, it is suggested that HRV and BRV parameters are relevant to drowsiness.