Assessing the impact of coupling RTT and RSSI measurements in fingerprinting Wi-Fi indoor positioning

Abstract

The field of Indoor Positioning Systems (IPS) is rapidly expanding due to the increasing need for accurate indoor localization. This research delves into the fingerprinting technique, a commonly used method in IPS, and advocates for coupling the Received Signal Strength Indicator (RSSI) to the Round-Trip Time (RTT) to boost its effectiveness. The primary incentive for this integration is to alleviate the network burden caused by the Wi-Fi RTT method while maintaining the system’s precision. Our goal is two-fold: firstly, we aim to find the ideal combination of RTT and RSSI features that a specific machine learning algorithm requires to supply precise and prompt position estimations for real-time applications. Secondly, we aim to reduce the number of RTT features needed, as they demand the addition of location traffic, which may saturate the network when multiple stations try to locate themselves. To meet these goals, a variety of machine learning models and several combinations of the available metrics (RTT and RSSI) have been assessed. Initial findings indicate that this combined approach significantly diminishes network overhead and enhances the scalability and effectiveness of the fingerprinting method, paving the way for further exploration in indoor localization.

Peer Reviewed

Postprint (author's final draft)