Discovering Statistics Using SPSS
Discovering Statistics Using SPSS
Pripayd: privacy friendly pay-as-you-drive insurance
Proceedings of the 2007 ACM workshop on Privacy in electronic society
IEEE Transactions on Intelligent Transportation Systems
GPS trajectory feature extraction for driver risk profiling
Proceedings of the 2011 international workshop on Trajectory data mining and analysis
Trip analyzer through smartphone apps
Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
The smart tachograph – individual accounting of traffic costs and its implications
PERVASIVE'06 Proceedings of the 4th international conference on Pervasive Computing
Personalized driving behavior monitoring and analysis for emerging hybrid vehicles
Pervasive'12 Proceedings of the 10th international conference on Pervasive Computing
Hi-index | 0.00 |
We evaluate a mobile application that assesses driving behavior based on in-vehicle acceleration measurements and gives corresponding feedback to drivers. In the insurance business, such applications have recently gained traction as a viable alternative to the monitoring of drivers via "black boxes" installed in vehicles, which lacks interaction opportunities and is perceived as privacy intrusive by policyholders. However, pose uncertainty and other noise-inducing factors make smartphones potentially less reliable as sensor platforms. We therefore compare critical driving events generated by a smartphone with reference measurements from a vehicle-fixed IMU in a controlled field study. The study was designed to capture driver variability under real-world conditions, while minimizing the influence of external factors. We find that the mobile measurements tend to overestimate critical driving events, possibly due to deviation from the calibrated initial device pose. While weather and daytime do not appear to influence event counts, road type is a significant factor that is not considered in most current state-of-the-art implementations.