Efficient Privacy-Preserving Fingerprint-Based Indoor Localization Using Crowdsourcing

Abstract

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 privacy-preserving localization scheme.