2017/09/21 by Bashar I. Ahmad, Ahmad, Bashar I., Patrick Langdon +7
Computer Science · Social Sciences · #Applications (stat.AP) #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Target Tracking and Data Fusion in Sensor Networks #Transportation Planning and Optimization
paper · pdf · doi:10.48550/arxiv.1709.07381
openalex publication_date 2017/09/21 · openalex created_date 2022/09/30 · openalex updated_date 2026/07/28
This paper proposes a probabilistic framework for the sequential estimation\nof the likelihood of a driver or passenger(s) returning to the vehicle and time\nof arrival, from the available partial track of the user location. The latter\ncan be provided by a smartphone navigational service and/or other dedicated\n(e.g. RF based) user-to-vehicle positioning solution. The introduced novel\napproach treats the tackled problem as an intent prediction task within a\nBayesian formulation, leading to an efficient implementation of the inference\nroutine with notably low training requirements. It effectively captures the\nlong term dependencies in the trajectory followed by the driver/passenger to\nthe vehicle, as dictated by intent, via a bridging distribution. Two examples\nare shown to demonstrate the efficacy of this flexible low-complexity\ntechnique.\n