Bluetooth low energy (BLE) based asset tagging system (BLE RSSI finger printing focus)

• Main Author: Li, Jefferson Zheng Jun
• Other Authors: Oh Hong Lye
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/166068
• Institution: Nanyang Technological University

Asset tracking is an important technology as it allows businesses to track and manage valuable assets. A key aim of this paper is to explore the efficacy of Bluetooth Low Energy (BLE) based asset tracking in an indoor environment. This paper will examine how to convert the received signal strength indicator (RSSI) values from BLE devices to said devices’ position within a fixed arena. A neural network model will be built additionally to evaluate these RSSI values, which often fluctuate and therefore hard to make sense of. The experimental results show significant improvements over past works with the inclusion of neural network models. This project will end off with a live demonstration to demonstrate the useability of this paper’s findings under real-world conditions.