Semi-Supervised Physics-Informed Genetic Fuzzy System for IoT BLE Localization

Abstract

<p>The numerous possible applications for Bluetooth Low Energy (BLE) Beacons constantly motivate researchers to come up with new methods to optimize the utilizations of beacons and improve the positioning accuracy while maintaining the cost to benefit balance. In this study, a novel method was proposed to optimize the localization of an indoor BLE positioning system with low beacon density in a real-world environment. The proposed method combines three major machine learning concepts (Semi-Supervised Learning, Informed Machine Learning, and Soft Computing) in its analysis pipeline and presents a different perspective to approaching Genetic Fuzzy Systems (GFSs). The presented method was competitive when benchmarked against a fully connected neural network and a kNN model. </p>

Machine Learning Assists IoT Localization: A Review of Current Challenges and Future Trends

“…Their proposed method used genetic fuzzy systems (GFSs) by combining machine learning concepts. They employed the proposed methods to localize smartphones by utilizing RSSI values from 13 beacons [ 53 ].…”

Use of Emerging Internet of Things Technologies for Developing Infrastructure-to-Vehicle Communication Systems

“…Many studies evaluated the use of BLE beacons for various IoT applications. The application that has been researched most extensively is the use of BLE beacons for indoor localization (22)(23)(24)(25). However, research on the use of BLE beacons in other applications is still scarce compared with its potential usefulness (26).…”

“…The broadcasted message can deliver a small amount of data and trigger a certain action in the receiving device. Because BLE beacons have the low power consumption of BLE technology, they typically have a long battery life (22). The range at which beacons can broadcast their identifiers typically ranges from few centimeters to tens of meters.…”