ViFi: Virtual Fingerprinting WiFi-Based Indoor Positioning via Multi-Wall Multi-Floor Propagation Model

Abstract

Widespread adoption of indoor positioning systems based on WiFi fingerprinting is at present hindered by the large efforts required for measurements collection during the offline phase. Two approaches were recently proposed to address such issue: crowdsourcing and RSS radiomap prediction, based on either interpolation or propagation channel model fitting from a small set of measurements. RSS prediction promises better positioning accuracy when compared to crowdsourcing, but no systematic analysis of the impact of system parameters on positioning accuracy is available. This paper fills this gap by introducing ViFi, an indoor positioning system that relies on RSS prediction based on Multi-Wall Multi-Floor (MWMF) propagation model to generate a discrete RSS radiomap (virtual fingerprints). Extensive experimental results, obtained in multiple independent testbeds, show that ViFi outperforms virtual fingerprinting systems adopting simpler propagation models in terms of accuracy, and allows a sevenfold reduction in the number of measurements to be collected, while achieving the same accuracy of a traditional fingerprinting system deployed in the same environment. Finally, a set of guidelines for the implementation of ViFi in a generic environment, that saves the effort of collecting additional measurements for system testing and fine tuning, is proposed.

ThingsLocate: A ThingSpeak-Based Indoor Positioning Platform for Academic Research on Location-Aware Internet of Things

“…• optimization of offline phase RSSI data collection-it was pointed out in Section 4.4 that the RSSI data collection carried out during the offline phase in the Environment scan step accounts for most of the time required for the setup procedure, and that this issue is inherent to the way WiFi fingerprinting works. Recently, however, a promising technique to solve this issue was proposed by the authors of the present work [48]. The technique, named virtual fingerprinting, allows reduction of the number of RPs to be processed (and the corresponding time) by at least one order of magnitude by generating synthetically the remaining ones using a deterministic channel model [49].…”

“…The ThingsLocate platform was deployed at the second floor of the Department of Information Engineering, Electronics, and Telecommunications (DIET) of Sapienza University of Rome, Rome, Italy, covering a total area of approximately 42 × 12 m 2 . The deployment took advantage of the testbed previously deployed in this location, described in detail in [48]. N RP = 72 RPs were identified, with an average distance between two RPs of approximately 3 m. In each RP q = 50 samples were averaged to counteract the impact of the channel variability on the fingerprinting database.…”

Fundamental Concepts and Evolution of Wi-Fi User Localization: An Overview Based on Different Case Studies

“…For estimation of the damping of walls and modeling of the FSPL , special semi-empiric models, such as the multi-wall model [ 34 , 35 ], can be applied. Semi-empirical means in this regard that the current surroundings are incorporated in the signal propagation estimation model.…”

Hapi

“…However, this increases the deployment and maintenance overhead significantly, particularly in buildings with a large number of floor-levels. ViFi [20] uses the Multi-Wall Multi-Floor propagation model [8] to automatically predict the APs' signal propagation and construct the multifloor fingerprint maps. However, theoretical models accuracy degrades significantly in uncontrolled environments [20,22].…”

“…ViFi [20] uses the Multi-Wall Multi-Floor propagation model [8] to automatically predict the APs' signal propagation and construct the multifloor fingerprint maps. However, theoretical models accuracy degrades significantly in uncontrolled environments [20,22]. Contrarily, Locus [18,19] is calibration-free and uses a heuristics-based algorithm to identify the user's floor.…”