MonoFi

Abstract

Indoor localization is a key component of pervasive and mobile computing. Due to the widespread use of WiFi technology, WiFi fingerprinting is one of the most widely utilized approaches for indoor localization. Despite advancements in WiFi-based positioning approaches, existing solutions necessitate a dense deployment of access points, time-consuming manual fingerprinting, and/or special hardware. In this paper, we propose MonoFi, a novel WiFi-based indoor localization system relying only on the received signal strength from a single access point. To compensate for the low amount of information available for learning, the system trains a recurrent neural network with sequences of signal measurements. MonoFi incorporates different modules to reduce the data collection overhead, boost the scalability and improves the deep model's generalization. The proposed system is deployed and assessed in comparison to existing WiFi indoor localization systems. Our experiments with different mobile phones show that the system can achieve a median localization error of 0.80 meters, surpassing the state-of-the-art results by at least 140%.