Clustering combined indoor localization algorithms for crowdsourcing devices: Mining RSSI relative relationship

Fingerprint matching is adopted by a large family of indoor localization schemes, where collecting fingerprints is inevitable but all consuming. Recent studies show that the crowdsourcing scheme could be utilized to perform fingerprints collecting with desirable performance price ratio; however, since the fingerprints are collected from various mobile devices with crowdsourcing, it is difficult to determine the reliability of the collected fingerprints. This paper proposes a novel fingerprint processing algorithm based on RSSI relative relationship rather than traditional ones depending on absolute RSSI values. Furthermore, we make RSSI relative relationship quantitative and combine it with clustering-based localization algorithms. Finally, we propose a practical clustering comparison algorithm applied with practical indoor location system, based on which we can analyze diverse devices´ clustering results derived from our proposed fingerprints processing algorithm and traditional distance based fingerprints extraction methods. Experimental results indicate that the whole set of localization scheme we proposed for practical indoor localization system has competitive location accuracy symbiosis with crowdsourcing fingerprints collecting.