A Platform for the Evaluation of Fingerprint Positioning

A Platform for the Evaluation of Fingerprint Positioning. S. Algorithms C. Laoudias, G. Constantinou, M. Constantinides, Nicolaou, D. Zeinalipour[ Contact: laoudias@ucy. ac. cy ] Yazti and C. G. Panayiotou on Android Smartphones Positioning System Architecture Goals and Contributions • Build an open Android smartphone platform Positioning scenario Mobile-based Network-assisted architecture for positioning and tracking inside buildings • Integrate two. Time: Measure the average time required in practice to perform positioning on smartphones • Execution efficient positioning algorithms, 1 Positioning developed in-house • and SNAP 2, Accuracy: Calculate the mean positioning error pertaining to a test dataset RBF • Power Consumption: Investigate the actual battery depletion during positioning with the Power. Tutor 3 utility • Evaluate the performance of several fingerprint -based positioning algorithms in terms of: • Low communication overhead: Avoids uploading the observed RSS fingerprint to the positioning server for estimating location. Radiomap RSS logs Distribution Server KIOS Center is estimated by the user and RSSApplication Find. Application Logger @ & security: location Meprivacy Server Experimental Evaluation Radiomap Distribution RSS Logger. User Find Me • Parameters not by the positioning server. 1. A User enters an indoor environment, featuring Wi. Fi APs. 2. His smartphone obtains the RSS radiomap and parameters from the local distribution server in a single communication round. 3. The client positions itself independently using only local knowledge and without revealing its personal state. Measurement Setup Features • Developed and. APs the 560 m 2, 9 to the Constructs around Connects Wi. Fi server • 105 reference distributes the for downloading the Android RSS API for locations radiomap and algorithm scanning and collecting • Train Data: 105 parameters to measurementsthe reference locations, clients selects number • User definedany of the 4200 fingerprints • samples RSS (40 available algorithms of. Parses all and log files per merges and location)them • Dual operation in a sampling interval mode single radiomap that • RSS data stored locally Test Data: 96 Online: Location is locations, with contains the mean RSS plotted on 1920 in a log file Google Maps fingerprints (20 per value fingerprint [outdoors] or GPS (Lat, Lon) fromtheper location) location floorplan map [indoors] [outdoors] or (X, Y) by • Selects and fine-tunes clicking on. Loads an Offline: floorplan algorithm-specific external file with map [indoors] test parameters iteratively RSS fingerprints to • User can contribute by log files to the assess the performance theusing validation RSS data of different algorithms system for building and updating the radiomap KNN WKNN MAP MMSE RBF SNAP Accuracy [m] KNN WKNN MAP MMSE RBF SNAP Time [msec] KNN WKNN MAP MMSE RBF SNAP Power [m. W] 1 C. Laoudias, P. Kemppi, C. Panayiotou, "Localization using RBF Networks and Signal Strength Fingerprints in WLAN", IEEE GLOBECOM, 2009, pp. 1 -6. 2 C. Laoudias, M. P. Michaelides, C. G. Panayiotou, "Fault Tolerant Fingerprint-based Positioning", IEEE ICC, 2011, pp. 1 -5. 3 Power. Tutor: A Power Monitor for Android-based mobile platforms, http: //powertutor. org DMSL Data Management Systems Laboratory Acknowledgements: This work is supported by the Cyprus Research Promotion Foundation and in part by the fifth author's Startup Grant, funded by the University of Cyprus.