Amelio-rater: Detection and Classification of Driving Abnormal Behaviours for Automated Ratings and Real-Time Monitoring
Date
2018
Journal Title
Journal ISSN
Volume Title
Type
Book chapter
Publisher
IEEE
Series Info
13th International Conference on Computer Engineering and Systems (ICCES) 2018;
Scientific Journal Rankings
Abstract
Real-time monitoring of the drivers may be a factor that would force them to drive safely. In this paper, we introduce a system named 'Amelio-Rater", that focuses on detection and classification of abnormal driving behaviours for automatically generating driver ratings and real-time monitoring. To reduce malicious ratings, the Amelio-rater introduces an automatic rating system which is calculated purely based on the driver's driving behaviours only. Each driver will be given his own Amelio-rater rate and a manual user rate. There are multiple types of driving abnormal behaviours monitored by the proposed system such as meandering, single weaves, sudden changing of lanes and speeding. The classification results achieved showed that the Amelio-rater reached an accuracy of 95%. Our experiments showed that the manual user rates given for the driving behaviour are not far from the rates given by Amelio-rater. Amelio-rater rates were very close to the actual rates given by the users
Description
MSA Google Scholar
Keywords
October University for University for Roads, Time series analysis, Automobiles, Intelligent sensors, Smart phones