Dempster-Shafer Theory-based Indoor Region Prediction with Single Wi-Fi Access Point for Static Object Localization

Indoor localisation has gained significant attention in recent years due to its applications in various domains, including robotics, asset tracking, and location-based services. Traditional indoor localisation systems rely on several access points or infrastructure, which are sometimes costly and challenging to establish. This paper investigates the viability of using a single access point for the indoor localisation of static objects. Initially, a dataset is recorded in the laboratory with ESP32 and a smartphone. After that, the dataset is utilised to train an algorithm that can infer the user’s location from current RSSI readings. Furthermore, the RSSI single feature is converted into five statistical features: 25%,50%, and 75% of quartiles, as well as min and max. The Dempster-Shafer Theory (DST) is used to classify the different regions. The localisation algorithm used in this system maps the RSSI values to appropriate locations inside the interior environment. The algorithm shows better results than several other machine learning algorithms.