Authors: Samuel Lawoyin; Ding-Yu Fei; Ou Bai; Xin Liu
Addresses: Department of Biomedical Engineering, Virginia Commonwealth University, Richmond, Virginia, USA ' Department of Biomedical Engineering, Virginia Commonwealth University, Richmond, Virginia, USA ' Department of Biomedical Engineering, Virginia Commonwealth University, Richmond, Virginia, USA ' School of Transportation, Science and Engineering, Harbin Institute of Technology, Harbin, China
Abstract: Each year, thousands of accidents and fatalities occur when drowsy and fatigued drivers operate motor vehicles. Steering Wheel Movements (SWM) monitoring is an important and well documented method for the detection of drowsy driving. Although the SWM method has been shown to be effective, it has not yet been widely deployed on motor vehicles owing to cost prohibitions and the complexity of implementation. An earlier article by the same authors introduced and demonstrated the efficacy of an accelerometer-based method for SWM monitoring. The residual question from the previous study pertains to the detection accuracy of the method. The current study evaluates the accuracy of the method in detecting drowsiness using data from eight persons. Electrooculography (EOG), Electroencephalography (EEG) and the percent of eyelid closures (PERCLOS) were used to label drowsy states for training Support Vector Machines (SVM) and Probabilistic Neural Networks (PNN). Results show that using solely accelerometer data accurately classifies driver drowsiness (80.65%). The high accuracy demonstrates that accelerometers can be a simple, non-obtrusive and cost-effective method to help proliferate the practical deployment of individual drowsy detection.
Keywords: drowsy drivers; accelerometers; sleep disorders; steering wheel movements; accidents; driver safety; driver fatigue; drowsiness detection; highway safety; accident prevention; vehicle safety; electrooculography; EOG; electroencephalography; EEG; eyelid closures; drowsy states; support vector machines; SVM; probabilistic neural networks; PNNs; driver drowsiness.
International Journal of Vehicle Safety, 2015 Vol.8 No.2, pp.165 - 179
Received: 24 Apr 2014
Accepted: 25 Jan 2015
Published online: 31 Mar 2015 *