Measuring the interest in a product or service in a public space, such as a trade show or a sales floor, is fundamentally important for the evaluation of the marketing strategies of businesses. As indoor location services gain popularity due to the absence of Global Positioning System (GPS) signal indoor, the use of Wi-Fi (802.11) and Bluetooth emerged as an alternative to track devices.
BluePIL was proposed in [1] as a fully passive system for Bluetooth device identification and localization designed as a distributed streaming architecture delivering results in near-real-time. It relies on parts of the Bluetooth address for device identification and a modified multi-lateration algorithm using a path loss model for device localization.
The objective of this thesis is to expand the scope of the evaluations (by deploying BluePIL in practice), and experimenting the method in different scenarios to identify calibration parameters of the sensors (e.g., adjust the RSSI values, signal loss parameters) and collect data that allow to increase the tracking accuracy.
[1] Bruno Rodrigues, Cyrill Halter, Muriel Franco, Eder John Scheid, Christian Killer, Burkhard Stiller: BluePIL: a Bluetooth-based Passive Indoor Localization Method; IFIP/IEEE International Symposium on Integrated Network Management (IM 2021), Bordeaux, France, May 2021, pp 1-9. URL: https://files.ifi.uzh.ch/CSG/staff/rodrigues/extern/publications/IM21-BluePIL.pdf.
Supervisors: Dr. Bruno Rodrigues
back to the main page