Cost-Efficient RSSI-Based Indoor Proximity Positioning, for Large/Complex Museum Exhibition Spaces

RSSI-based proximity positioning is a well-established technique for indoor localization, featuring simplicity and cost-effectiveness, requiring low-price and off-the-shelf hardware. However, it suffers from low accuracy (in NLOS traffic), noise, and multipath fading issues. In large complex spaces, such as museums, where heavy visitor traffic is expected to seriously impact the ability to maintain LOS, RSSI coupled with Bluetooth Low Energy (BLE) seems ideal in terms of market availability, cost-/energy-efficiency and scalability that affect competing technologies, provided it achieves adequate accuracy. Our work reports and discusses findings of a BLE/RSSI-based pilot, implemented at the Museum of Modern Greek Culture in Athens, involving eight buildings with 47 halls with diverse areas, shapes, and showcase layouts. Wearable visitor BLE beacons provided cell-level location determined by a prototype tool (VTT), integrating in its architecture different functionalities: raw RSSI data smoothing with Kalman filters, hybrid positioning provision, temporal methods for visitor cell prediction, spatial filtering, and prediction based on popular machine learning classifiers. Visitor movement modeling, based on critical parameters influencing signal measurements, provided scenarios mapped to popular behavioral models. One such model, “ant”, corresponding to relatively slow nomadic cell roaming, was selected for basic experimentation. Pilot implementation decisions and methods adopted at all layers of the VTT architecture followed the overall concept of simplicity, availability, and cost-efficiency, providing a maximum infrastructure cost of 8 Euro per m2 covered. A total 15 methods/algorithms were evaluated against prediction accuracy across 20 RSSI datasets, incorporating diverse hall cell allocations and visitor movement patterns. RSSI data, temporal and spatial management with simple low-processing methods adopted, achieved a maximum prediction accuracy average of 81.53% across all datasets, while ML algorithms (Random Forest) achieved a maximum prediction accuracy average of 87.24%.