A new optimization approach for indoor location based on Differential Evolution

The growth of Location Based Services and Location Aware Services in indoor environments has focused the attention of the research community on indoor location systems, especially on those based on WLAN networks and Received Signal Strength (RSS). Despite the advances reached, the development of reliable, accurate and low-cost indoor location systems still remains as an open problem. In this work, we focus on a specific class of location methods where the position of a Mobile Station (MS) is estimated by optimizing a cost function. As far as we know, the optimization models for indoor location proposed so far, only consider the current RSS measurements to estimate the position. In this paper, we propose an optimization approach that uses both current and past measurements to estimate the MS location. To solve the underlying optimization problem we use a Differential Evolution algorithm. The experimentation done over a simulated and a real scenario shows, on the one hand, that using past and current measurements we obtain more accurate and robust position estimations, and on the other hand, that our proposal is competitive versus other high-performing location methods proposed in the literature.