Use of Data Recorder for Driver Rating

Data recorders are generally used in vehicles for post-crash analysis. We propose a new approach of using this device to rate the drive quality of a driver. Whereas vehicles in the West generally operate in an optimal environment with high-quality road infrastructure, the situation in developing countries is different. The vehicles are often underpowered, sub-optimally maintained, over-loaded and ply on poor-quality roads where the driving style greatly affects the safety aspects and performance of the vehicle. Also in such an environment, fuel cost is relatively high. By improving the driving style, fuel economy can be improved by 15-20%. Fleet Managers can use the resulting system to study driver behavior and to improve the performance and safety of their services. An optimal driver-model is developed using data mining techniques. This model rates driving style on fuel-economy basis by analyzing the driver's interaction data with the vehicle. Preliminary results from the initial work are presented in this paper.