Answers are grounded in this paper and cite their sources.
A common problem faced by first-year students, visitors and service staff is finding specific rooms in large campus buildings. Satellite navigation does not work indoors, and most commercially available indoor localization solutions require expensive infrastructure and a constant internet connection. This paper presents CampusNav-32, a low-cost, fully offline solution for room-level localization based on Bluetooth Low Energy (BLE) received signal strength indicator (RSSI) fingerprinting. Eight low-cost BLE beacons were placed along a representative corridor on campus, and a fingerprint database of 31 reference points was built over four survey sessions. A k-Nearest Neighbour (k-NN) classifier, benchmarked against a Random Forest, runs directly on a smartphone or an ESP32 microcontroller, so no server or internet connection is required. In on-site testing with 150 independent scans across five zones, the system identified the correct room 130 times, an overall accuracy of 86.7% (95% Wilson interval: 80.3–91.2%), ranging from 80% to 93% per zone. Accuracy was lowest in the open corridor and around the office, where the coverage of several beacons overlaps; a simple analysis of the fingerprint database shows that these are also the zones whose signal signatures lie closest together. The hardware for the whole block cost approximately ₹3,250. The system design, survey methodology, pre-processing, classification and confidence output are described, and failure modes, limitations and privacy considerations are analysed so that other institutions can replicate and extend the system.
No takes yet. Share an insight, caveat, or question.
Hage et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: