IoT-TD: IoT Dataset for Multiple Model BLE-based Indoor Localization/Tracking

Abstract

Bluetooth Low Energy (BLE) is one of the key enabling technologies of the emerging Internet of Things (IoT) concept. When it comes to BLE-based dynamic indoor tracking, however, due to drastic fluctuations of the Received Signal Strength Indicator (RSSI), highly acceptable accuracies are not yet achieved. Although very recent introduction of BLE v 5.1 promises prosperous future for BLE-based dynamic tracking, the following two key issues are in the path: (i) Despite of being in the age of big data with huge emphasis on reproducibility of research, there is no unified dataset with precise ground truth available for performing dynamic BLE-based tracking, and; (ii) The main focus of existing works are on utilization of stand-alone models. The paper addresses these gaps. At one hand, we introduce a reliable dataset, referred to as the IoT-TD, leveraging specific set of four optical cameras to provide ground truth with millimeter accuracies. The introduced IoT-TD dataset consists of RSSI values collected from five BLE sensors together with synchronized Inertial Measurement Unit (IMU) signals from the target's mobile device. On the other hand, the paper introduces a multiple-model dynamic estimation framework coupling RSSI-based particle filtering with IMU-based Pedestrian Dead Reckoning (PDR). Experimental results based on the IoT-TD dataset corroborate effectiveness of multiple modeling fusion frameworks for providing enhanced BLE-based tracking accuracies.