Indoor Location in WLAN Based on Competitive Agglomeration Algorithm

In the area of Wireless Local Area Network (WLAN) based indoor localization, the k-nearest neighbors (KNN) fusion clustering algorithm has been studied extensively. But the number of the clustering and the value of K is set manually and fixed, so it can’t adapt to the environment changes. Besides, the algorithm localization with a single Received Signal Strength (RSS), and ignored other deeper information such as the physical location information. Aiming at the shortcomings of the fusion algorithm, in this paper, we proposed a novel indoor localization algorithm based on competitive agglomeration (CA). The algorithm soft partition radio map based on RSS and physical location information in succession, and select the clustering number based on real time information in the environment to estimate user’s position coordinates. Finally, based on the extensive experiments conducted in a real WLAN indoor environment, our proposed algorithm is proved to outperform traditional positioning algorithm.