A Computationally Efficient Approach to WLAN Localization based on Multiple Filters

Accurate indoor positioning of mobile users is a crucial operation for location aware computer applications. However, the complex and nonstationary propagation characteristics of indoor environments and the large number of different mobile devices make difficult to employ classical geometrical approaches. In this work we examine the application of sequential Bayesian approaches to this problem and propose a computationally efficient implementation based on Multiple Filters (MFs). Both simulated and real data are used to assess the proposed algorithm, showing that the MF approach allows to obtain a significant reduction of the computational complexity with the same estimation accuracy of state-of-the-art sequential methods.