MIFF: Human Mobility Extractions with Cellular Signaling Data under Spatio-temporal Uncertainty
summary
A framework called MIFF fuses cell-tower signaling traces before map matching and uses a confidence DTW (CDTW) similarity to find homogeneous traces from a month of operator SD and handheld SD in Hefei and Shanghai. Fusion plus map matching improves road-level extraction by 5.0% on Point correct matching index and reduces Geographic Error by 68.5% on average versus HMM/CTS baselines; evaluated across rail, car, bus, and bike and implemented preprocessing, homogeneous-trace search, and fusion.
AI-written summary · about
related talks
06mExtending Coverage of Stationary Sensing Systems with Mobile Sensing Systems for Human Mobility ...
06mPMF: A Privacy-preserving Human Mobility Prediction Framework via Federated Learning
06mReal-time Travel Time Estimation with Sparse Reliable Surveillance Information
19mSimulation-based origin destination matrix reduction: a case study of Helsinki city area
06mCellPred: A Behavior-aware Scheme for Cellular Data Usage Prediction
31mWi‑Fi/GSM Geolocation in Large Cities Using ML for 30 Million Users
28m"Where, When, Why, and How: Directi
22mUsing big data from RF monitoring...