Increasing Interference Robustness of WiFi Fingerprinting by Leveraging Spectrum Information

RF-based indoor localization is constantly gaining popularity, and WiFi-based fingerprinting algorithms belong to the most promising candidates due to their well-known advantages. While it is known that RF interference can adversely influence the accuracy of those algorithms, it is still unclear if this effect could be efficiently mitigated. To this end, we demonstrate the impact and propose a procedure for reducing the influence of RF interference on WiFi beacon packets RSSI-based fingerprinting algorithms. The proposed procedure adjusts the RSSI measurements based on estimates of their variability caused by RF interference. For estimating the variability in RSSI measurements, the procedure leverages information about the spectrum power levels in the frequency band on which the fingerprinting algorithm performs. The proposed procedure can be inserted in the usual workflow of fingerprinting algorithms. We experimentally compared the performance of two well-known WiFi-based fingerprinting algorithms without and with the proposed interference mitigation procedure. Our experimental evaluation in different interference scenarios shows that the proposed procedure for mitigating the influence of RF interference significantly improves the localization accuracy, while it does not notably increase the latency of evaluated fingerprinting algorithms.