WiFi-based Indoor Localization Using a Continuous Space Estimator From Topological Information
N. Hernández, M. Ocaña, J. M. Alonso and E. Kim
Proceedings of the 2015 International Conference on Indoor Positioning and Indoor Navigation. 2015.
Abstract: Although lot of research has taken place in WiFi indoor localization systems, it remains as an open problem and their accuracy can still be improved. When designing this kind of systems, fingerprint-based methods are a common choice. The problem with fingerprint-based systems comes with the need of site-survey the environment which is effort-consuming, especially when the required localization resolution is high. In this paper, we propose an approach to increase the resolution of WiFi fingerprint-based localization systems. This approach uses a Support Vector Regression algorithm that will estimate the Received Signal Strength for unknown coordinates of the environment. This way, the resolution of the system will be increased without the need of site-surveying a high number of positions. Experiments, performed in a real environment, show that the proposed method could be used to improve the resolution of fingerprint-based indoor WiFi localization systems.