Toward Translating Raw Indoor Positioning Data into Mobility Semantics

Indoor mobility analyses are increasingly interesting due to the rapid growth of raw positioning data obtained from IoT infrastructure. However, high-level analyses are still in urgent need of a concise but semantics-oriented representation of the mobility implied by raw data. We study the problem of translating indoor positioning data into mobility semantics that describe an object's mobility event (What) someplace (Where) at some time (When). The problem is non-trivial mainly because of the inherent errors in uncertain, discrete raw data. We propose a three-layer framework to tackle the problem. In the cleaning layer, we design a cleaning method that eliminates positioning errors by considering indoor mobility constraints. In the annotation layer, we propose a density-based splitting method to divide positioning sequences into snippets according to underlying mobility events, and a semantic matching method to make proper annotations for split snippets. In the complementing layer, we devise an inference method that makes use of indoor topology and mobility semantics already obtained to recover the missing mobility semantics. The experiments demonstrate that our solution is efficient and effective on both real and synthetic data. For typical queries, our solution's resultant mobility semantics lead to more precise answers but incur less execution time.