Title: Accident prevention and prescription by analysis of vehicle and driver behaviour
Authors: Mathews Peter; Shriram K. Vasudevan
Addresses: Department of Mechanical Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham (University), Coimbatore, Tamilnadu, India ' Department of Computer Science and Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham (University), Coimbatore, Tamilnadu, India
Abstract: Vehicle acceleration when analysed against location gives those locations where there are more sudden accelerations and decelerations. Lateral acceleration of vehicle when analysed against the driver identity can reveal if the driver is rash or not, assuming a driver is rash if there are higher incidents of sudden steering movements. Upon identification of the acceleration and location data, they are stored against the driver ID. A set of algorithms are proposed in the paper, and are implemented to predict accidents. Other implementation includes alerting the driver if an accident is predicted, and also recording and saving audio and visuals if an accident is detected.
Keywords: vehicle acceleration; vehicle deceleration; vehicle accident; vehicle; location; driver behaviour; steering; Android; Arduino; pattern; prediction.
International Journal of Embedded Systems, 2017 Vol.9 No.4, pp.328 - 336
Received: 15 Sep 2015
Accepted: 05 Apr 2016
Published online: 27 Aug 2017 *