Inferring truck activities using privacy-preserving truck trajectories data

Global Navigation Satellite System (GNSS) data is an inexpensive and ubiquitous source of activity data. Positioning (GPS) example such Although there have been several studies about inferring device using GPS from a consumer device, freight presents unique challenges for having low variable frequency, long transmission gaps, frequent unpredictable ID resetting preserving privacy. This study aims to provide end-to-end, generic analytical framework infer multiple aspects truck as stops, trips tours. We use popular existing methods construct the processing pipeline insights into their practical usage. also propose improved filters different address found in privacy-preserving across four weeks greater Philadelphia region with frequency ranging one second hours perform experiments validate our methods. Our findings indicate that auxiliary information land can be helpful fine tuning stop inference,but spatio-temporal contained timestamped pings still most powerful false identification. find combination simple clustering techniques way fast reasonable same stop.