Edge-Based Indoor Bluetooth Low Energy Fingerprinting for Low-Cost, Offline Room-Level Localization in College Campus Buildings

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.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-16
DOI
https://doi.org/10.5281/zenodo.24275850
Primary Topic
Indoor and Outdoor Localization Technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Edge-Based Indoor Bluetooth Low Energy Fingerprinting for Low-Cost, Offline Room-Level Localization in College Campus Buildings

Om Kadu, Sumit Fulzele, Prabhat Madke, Om Hage et al.
1 links
Zenodo (CERN European Organization for Nuclear Research)
Indoor and Outdoor Localization Technologies
article

Edge-Based Indoor Bluetooth Low Energy Fingerprinting for Low-Cost, Offline Room-Level Localization in College Campus Buildings

Om Kadu, Sumit Fulzele, Prabhat Madke, Om Hage, Nishith Gajjalwar, Om Ebitwar
article en

Abstract

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.

Zenodo (CERN European Organization for Nuclear Research)
Indoor and Outdoor Localization Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon