Indoor Positioning in WLAN Environment Based on Support Vector Regression and Space Partitioning

Abstract:

Indoor positioning system in wireless local area network (WLAN) has been a subject of intensive research due to its cost effectiveness and reasonable positioning accuracy. A new WLAN indoor positioning algorithm based on support vector regression (SVR) and space partitioning is proposed. The whole positioning environment is partitioned into several subspaces by combining k-means clustering method and binary support vector classifiers (SVC). Then the mapping function between received signal strength (RSS) and the physical space is established by SVR machine for each subspace. Subspace with much smaller physical range means more compact input feature space and leads to the enhancement of generalization capability for each SVR machine. The proposed algorithm and other well-known positioning algorithms are carried and compared in a real WLAN environment. Experimental results show that the proposed algorithm achieves 14.6 percent (0.31m) improvement than the single SVR algorithm in the sense of mean positioning error.

• Periodical: Advanced Materials Research (Volumes 204-210)
• Pages: 1599-1602
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.204-210.1599
• Online since: February 2011
• Authors: Zhi An Deng, Yu Bin Xu, Di Wu
• Keywords: Indoor Positioning, Space Partitioning, Support Vector Regression (SVR), Wireless Local Area Network (WLAN)

References

[1] Y. Gu, A. Lo, and I. Niemegeers: IEEE Commu. Surveys & Tutorials, vol. 11 (2009), p.13–32.

[2] A. Kushki, K. Plataniotis, and A. Venetsanopoulos: IEEE Transactions on Mobile Computing, vol. 9 (2010), pp.405-419.

[3] M. Brunato, and R. Battiti: Computer Networks, vol. 47 (2005), p.825–845.

[4] U. Ahmad, and A. V. Gavrilov, et al: Neurocomputing, vol. 71 (2008), pp.2657-2669.

[5] P. Bahl and V. N. Padmanabhan: Proc. INFOCOM, 2000, p.775–784.

[6] M. Youssef, A. Agrawala, and A. U. Shankar: Pervasive Comput. Commun., 2003, p.143–150.

[7] K Y. Chen, and Q. Yang, et al: IEEE Transactions on Knowledge and Data Engineering, vol. 18 (2006), pp.877-888.

[8] S. H. Fang, T. N. Lin, and K. C. Lee: IEEE Transactions on Wireless Communications, vol. 7 (2008), p.3579–3588.

[9] V. N. Vapnik: IEEE Transactions on Neural Networks, vol. 10 (1999), pp.988-999.

[10] Z. Wu, C. Li, and J. Yin: IEEE Transactions on Mobile Computing, vol. 6 (2007), pp.311-321.

[11] S. Theodoridis and K. Koutroumbas: Pattern Recognition, 4th Edition. Chapter 5, Academic Press, (2009).