MonoDCell - A Ubiquitous and Low-Overhead Deep Learning-based Indoor Localization with Limited Cellular Information.

The demand for a ubiquitous and accurate indoor localization service is continuously growing. Despite the pervasive nature of cellular-based solutions, their localization quality depends on the number of cell towers provided by the phone, which is typically limited. Specifically, according to the standard, any cell phone can receive signal strength information from up to seven cell towers. However, the majority of cell phones usually return only the associated cell tower information, significantly limiting the amount of information available to the location determination algorithm, degrading its performance. In this paper, we present MonoDCell: a novel cellular-based indoor localization system based on a deep long short-term memory (LSTM) network. The system utilizes the signal strength history from only the associated cell tower to achieve a fine-grained localization. MonoDCell incorporates different modules that lessen the data collection effort and improve the deep model's generalization and robustness against noise. We deployed MonoDCell using different Android devices in two realistic testbeds of different sizes. Evaluation results show that it can track the user with median location error of 0.95m and 1.42m in the smaller and the larger testbeds, respectively. This accuracy demonstrates the superiority of MonoDCell compared to the state-of-the-art systems by at least 202% in both testbeds considered. This highlights the promise of MonoDCell as an accurate and ubiquitous localization system.