Crowdsourcing-Based Indoor Localization with Knowledge-Aided Fingerprint Transfer

Precise indoor localization is a key requirement for the fifth-generation (5G) and beyond wireless communication systems with applications. To that end, many high accuracy signal fingerprint-based localization algorithms have been proposed. Most of these algorithms, however, face the problem of performance degradation in indoor environments, when the propagation environment changes with time. In order to address this issue, the crowdsourcing approach has been recently adopted, where the fingerprint database is frequently updated via user reporting. These crowdsourcing techniques still require precise indoor floor plans and fail to provide satisfactory accuracy. In this paper, we propose a low-complexity self-calibrating indoor crowdsourcing localization system that combines historical fingerprints with frequently updated fingerprints for high precision user positioning. We present a multi-kernel transfer learning approach that exploits the inner relationship between the historical and updated channel state information (CSI). Our indoor laboratory experimental results using Nexus 5 smartphones at 2.4GHz with 20MHz bandwidth have shown the feasibility of the proposed approach to achieve about one-meter level accuracy with a reasonable fingerprint update overhead.