MIFF

Human Mobility Extraction with cellular Signaling Data (SD) is essential for human mobility understanding, epidemic control, and wireless network planning. SD log the detailed interactions between cellphones and cellular towers, but suffer from a spatio-temporal uncertainty problem due to cellular network tower-level load rebalancing (switching users between towers) and cellphone usage activities. To date, most models focus on utilizing better data like RSSI or GPS, do not directly address uncertainty. To address the SD uncertainty issue, we utilize two insights based on (i) individuals' regular mobility patterns and (ii) common co-movement mobility patterns between cellphone users as suggested by fundamental human mobility nature. Accordingly, we design a Multi-Information Fusion Framework (MIFF) to assist in extracting road-level human mobility based on cell-tower level traces. To evaluate the effectiveness of MIFF, we conduct experiments on one-month SD obtained from a cellular service operator, and SD manually collected by handheld mobile devices in two cities in China. Four transportation modes, namely railways, cars, buses, and bikes are evaluated. Experimental results show that with MIFF, our road-level trajectory extraction accuracy can be improved by 5.0% on Point correct matching index and 68.5% on Geographic Error on average.