Driver fatigue detection using approximate entropic of steering wheel angle from real driving data

Abstract

This paper presents a steering-wheel-angle-based driver fatigue detection method for real driving conditions. This method extracts approximate entropy (ApEn) feature from recorded steering wheel angle (SWA) signal with a decision-tree-like classifier to identify the driving fatigue level. ApEn is extracted from fixed-size sliding window on real-time SWA series. To further exploit the in-depth information of SWA, additional features including intervalpercentage, deviation, kurtosis and complexity value of ApEn are extracted and applied to the designed classifier. The experiment is set on 14.68 h of real road driving, the collected data has been segmented into three fatigue levels ("awake, "drowsy', "very drowsy'). The classification result showed that the proposed method achieves an averaged accuracy of 82.07%. These results confirm that the proposed method is effective in the detection of real-time driver fatigue.