A Novel Algorithm Based on Clustering and Access Points Selection for Indoor Fingerprint Localization

With the growing popularity of location-based service (LBS), wireless local area networks (WLAN) indoor positioning has gained widespread attention. Unlike the traditional algorithm concentrating on positioning accuracy, we discuss how to improve the real-time property in WLAN indoor fingerprinting localization systems. In this paper, we present a novel algorithm which first divides the positioning area into sub-areas utilizing k-means clustering, and then selects appropriate access points (APs) for positioning to make the calculated amount as less as possible. By collecting data and performing in the real WLAN environment, our proposed algorithm shows high positioning accuracy while the computational burden has been decreased almost 93.7%.

[1]  Moustafa Youssef,et al.  WLAN location determination via clustering and probability distributions , 2003, Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003. (PerCom 2003)..

[2]  Qiang Yang,et al.  Adaptive Temporal Radio Maps for Indoor Location Estimation , 2005, Third IEEE International Conference on Pervasive Computing and Communications.

[3]  Shih-Hau Fang,et al.  A Novel Algorithm for Multipath Fingerprinting in Indoor WLAN Environments , 2008, IEEE Transactions on Wireless Communications.

[4]  Moustafa Youssef,et al.  The Horus WLAN location determination system , 2005, MobiSys '05.

[5]  Sinan Gezici,et al.  A Survey on Wireless Position Estimation , 2008, Wirel. Pers. Commun..

[6]  Hui Xiong,et al.  K-means clustering versus validation measures: a data distribution perspective , 2006, KDD '06.

[7]  Hui Xiong,et al.  Information-Theoretic Distance Measures for Clustering Validation: Generalization and Normalization , 2009, IEEE Transactions on Knowledge and Data Engineering.