Spatially localized and joint access point selection for Wi-Fi indoor positioning

Wi-Fi indoor positioning system has received increasing interest in pervasive computing applications due to its low cost and satisfactory accuracy. To obtain high positioning accuracy based on source limited devices, various AP selection strategies have been proposed to select the most discriminant APs for positioning. In this paper, we propose a spatially localized AP selection method based on joint location information gain. In contrast to traditional AP selection methods which measure the discriminant ability of APs independently, we consider choosing APs jointly. By considering the correlation of the discriminant ability between different APs, more accurate measure of the discriminant ability of APs can be taken. Furthermore, since the optimal AP selection solution varies spatially, we incorporate a location clustering method to localize AP selection and subsequent positioning process. Finally, support vector regression (SVR) algorithm is combined to estimate the location. Experiments are carried in a realistic Wi-Fi indoor environment. Experimental results show that, by using the localized joint AP selection strategy, the proposed positioning method achieves a high-level accuracy while reducing the energy consumption on client devices significantly.