Detection system of unsafe driving behavior significant for cognitive dysfunction patients

Abstract

Cognitive dysfunction patient could have symptoms such as attention disorder, execute function disorder and so on. These symptoms may cause unsafe driving in daily life. The degree of these symptoms can be evaluated by neuropsychological examination, however, the correspondence relationship between these symptoms and unsafe driving is uncertain. Therefore, it is difficult to judge the patient’s driving capability with only neuropsychological examination. Though evaluation methods such as driving simulator are also used alongside neuropsychological examination, driving simulator has limitations on reproducibility of the acceleration shift, visual resolution or coverage angle of the display. To solve this problem, we are developing an unsafe driving detection system to be used in a real car, based on an analysis of the cognitive dysfunction patient’s behaviors. It requires some small wireless sensors measuring triaxial angular velocity and acceleration to be attached on user’s head and steering wheel, and GPS sensor on a car. This experiment which uses a real car was conducted in our designed “private course” in Toyama Driving Education Center Japan. In order to confirm various expected driving actions, the subject, 13 cognitive dysfunction patients and 12 adults without cognitive dysfunction, were equipped with small wireless sensors. As a result of video analysis, two hypotheses can be made about the difference between the cognitive dysfunction patients and adults without cognitive dysfunction. One is the sequence of the “safety checking action” and “lane changing operation” when changing lane, and another is the reacceleration when decelerating on planned slowdown from high speed. According to the result of the sensor data analysis, the significant difference is confirmed on chi-square test same as in video analysis.