A Novel WLAN Indoor Positioning Algorithm Based on Positioning Characteristics Extraction

Much attention has been paid to WLAN indoor positioning algorithm for its high accuracy and low cost to meet the location based services (LBS). This paper proposes a novel positioning algorithm based on positioning characteristics extraction in WLAN indoor environment. Each RSS signal from an individual access point is taken as input of the RBF neural networks to establish the mapping between RSS signal and position coordinate. The RSS signal with the lower training error is selected as the positioning characteristic for its strong dependency with position. Then all the selected RSS signals are combined to train the RBF neural networks for indoor positioning. Experimental results show that much higher positioning accuracy is obtained by the proposed algorithm than traditional positioning algorithms.