Efficient Privacy-Preserving Fingerprint-based Indoor Localization using Crowdsourcing

Indoor localization has been widely studied due to the inability of GPS to function indoors. Numerous approaches have been proposed in the past and a number of these approaches are currently being used commercially. However, little attention was paid to the privacy of the users especially in the commercial products. Malicious individuals can determine a client's daily habits and activities by simply analyzing their WiFi signals and tracking information. In this paper, we implemented a privacy-preserving indoor localization scheme that is based on a fingerprinting approach to analyze the performance issues in terms of accuracy, complexity, scalability and privacy. We developed an Android app and collected a large number of data on the third floor of the FIU Engineering Center. The analysis of data provided excellent opportunities for performance improvement which have been incorporated to the privacypreserving localization scheme.