Enhancing Indoor Asset Tracking: IoT Integration and Machine Learning Approaches for Optimized Performance

Abstract

Indoor asset tracking entails the surveillance and governance of the position and movement of tangible assets within enclosed spaces, including warehouses, hospitals, and workplaces. Indoor asset tracking systems employ technologies such as Radio Frequency Identification (RFID), Bluetooth Low Energy (BLE), Wi-Fi, and UWB (Ultra-Wideband) to deliver real-time visibility and precise placement of goods. This research introduces indoor asset tracking with IoT and machine learning. Indoor asset tracking has advanced significantly with the incorporation of Internet of Things (IoT) and machine learning technology. The Internet of Things facilitates the effortless acquisition of real-time data from diverse sensors and devices, while machine learning algorithms analyze this data to deliver precise tracking and predictive analytics. This combination enables the tracking of asset locations, conditions, and movements in indoor settings, including storage areas, hospitals and different industries. This study gathers data from the BLE tracker, which transmits information to the Lora gateway. This research utilizes supervised learning methodologies, including Support Vector Machines (SVMs), K-Nearest Neighbors (KNNs), and Neural Networks (NN). The F-score, recall, precision, and accuracy are employed for evaluation purposes. The experimental results indicate that the KNN model achieves the best accuracy of 80.5%.