2014/12/01 by Prithu Banerjee, Sayan Ranu, Sriram Raghavan
Computer Science · Medicine · Social Sciences · #Artificial intelligence #Computer science #Computer vision #Data Management and Algorithms #Data mining #Data-Driven Disease Surveillance #Enhanced Data Rates for GSM Evolution #Gibbs sampling #Global Positioning System #Graph #Human Mobility and Location-Based Analysis #Inference #Sampling (signal processing) #Theoretical computer science #Trajectory #cs.DB
paper · pdf · doi:10.1109/icdm.2014.41
openalex publication_date 2014/12/01 · arxiv created 2016/03/24 · arxiv updated 2016/03/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The explosion in the availability of GPS-enabled devices has resulted in an abundance of trajectory data. In reality, however, majority of these trajectories are collected at a low sampling rate and only provide partial observations on their actually traversed routes. Consequently, they are mired with uncertainty. In this paper, we develop a technique called Infer Tra to infer uncertain trajectories from network-constrained partial observations. Rather than predicting the most likely route, the inferred uncertain trajectory takes the form of an edge-weighted graph and summarizes all probable routes in a holistic manner. For trajectory inference, Infer Tra employs Gibbs sampling by learning a Network Mobility Model (NMM) from a database of historical trajectories. Extensive experiments on real trajectory databases show that the graph-based approach of Infer Tra is up to 50% more accurate, 20 times faster, and immensely more versatile than state-of-the-art techniques.