Abstract—Recently, there is an increasing interest in WIFI positioning systems due to the cost and availability of this technology. However, the main problem in WIFI-based localization is the severe fluctuation of received signal strength even for a static client. In this paper, we consider the localization of a wireless device using a dynamic neural network. Many types of dynamic neural networks are simulated, and then we will choose the one that gives best estimations to do real experiments. The proposed approach demonstrates significant improvements in the experiments and simulation.
Index Terms—Indoor localization, neural networks, RSS time varying, WIFI positioning systems.
The Authors are with the Beijing University of Aeronautics and Astronautics, China (e-mail: email@example.com; firstname.lastname@example.org).
Cite:Djabri Fahed and Rongke Liu, "Wi-Fi-Based Localization in Dynamic Indoor Environment Using a Dynamic Neural Network," International Journal of Machine Learning and Computing vol. 3, no. 1, pp. 127-131, 2013.