An Attempt to Predict Point in Time with High Risk of Crash Using Psychological Rating on Drowsiness and X-Bar Chart of Behavioral Measures

A procedure for predicting the point in time with high risk of crash before the point in time of virtual accident was proposed using X-bar chart of the behavioral measures during a simulated driving task. The tracking error, the back pressure, the sitting pressure (COP movement on the sitting surface), the horizontal neck bending angle, and the vertical neck bending angle were measured during a driving task on the driving simulator. As a result of applying the proposed method to these data, we could identify the point in time with high risk of crash before the point in time of virtual accident occurred for nine participants out of ten. The time interval between the point in time with high risk of crash and the point in time of virtual accident ranged from 136 s to 526 s. As for the other one participant, the point in time with high risk of crash was identified 9 s after the point in time of virtual accident. In such a way, it has been verified that the proposed procedure for predicting the point in time with high risk of crash is effective and promising for warning drivers of the high risky state of crash.