Johannes Paefgen

GPS trajectory feature extraction for driver risk profiling

In this paper we develop a method and relevant feature constructs for the measurement of accident risk exposure from a large sample of real-world GPS data that includes accident and accident-free drivers. For trip frequency and accumulated driven distance features, an evaluation of their discriminatory power is given based on computational results. In our conclusion, we briefly discuss suitable classification approaches and limitations arising from external validity considerations.

Inferring usage characteristics of electric bicycles from position information

This paper describes an experimental setup for the analysis of e-bike usage characteristics based on GPS data. Usage characteristics include parameters such as average and maximum velocity, trip lengths and distribution over daytime. Based on high resolution position measurement these parameters are extracted and compared to other studies on both e-bikes and conventional bicycles. We show that applying location technology to concurrent monitoring of a fleet of e-bikes yields higher quality in terms of resolution and accuracy (1), and is less intrusive (2) than obtaining these data by conventional user surveys. The findings form a proof-of-concept for the adoption of location technology to transportation and behavioral sciences and suggest further interdisciplinary collaboration in these fields.