Authors: Munaf Salim Najim Al-Din; Atef Saleh Al-Mashakbeh
Addresses: Department of Electrical and Computer Engineering, University of Nizwa, Nizwa, Sultanate of Oman ' Department of Electrical Engineering, Tafila Technical University, P.O. Box 179, Tafila 66110, Jordan
Abstract: In recent years, the use of smartphones has grown significantly due to the increase in their computational capabilities and the integration of advanced sensor technologies. This prevalence of smartphones and advances in machine learning have greatly contributed to the field of vehicular applications in terms of accessible, available and cost. Nevertheless, the accuracy of these applications critically depends on the calibration and pre-processing techniques that is needed to mitigate these problems. This study proposes a set of simple calibration and pre-processing techniques to enhance the accuracy of a smartphone-based driving event detection and classification system. Furthermore, the paper presents a simple and effective approach for the identification and classification of driving events. The approach is based on separating the identification and the classification processes. The dynamic time warping (DTW) technique is used for the identification, while statistical and time metrics features are used for the classification. Results obtained show a high accuracy rate.
Keywords: smartphone sensors calibration; driving events detection; driving manoeuvres classification.
International Journal of Nanoparticles, 2020 Vol.12 No.1/2, pp.152 - 173
Received: 13 Jan 2019
Accepted: 23 Jul 2019
Published online: 24 Mar 2020 *