Positioning in WLAN environment by use of artificial neural networks and space partitioning

  • Miloš N. Borenović
  • Aleksandar M. Nešković


Short range wireless technologies such as wireless local area network (WLAN), Bluetooth, radio frequency identification, ultrasound and Infrared Data Association can be used to supply position information in indoor environments where their infrastructure is deployed. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. In this paper, the position determination by the use of artificial neural networks (ANNs) is explored. The single ANN multilayer feedforward structure and a novel positioning technique based on cascade-connected ANNs and space partitioning are presented. The proposed techniques are thoroughly investigated on a real WLAN network. Also, an in-depth comparison with other well-known techniques is shown. Positioning with a single ANN has shown good results. Moreover, when utilising space partitioning with the cascade-connected ANNs, the median error is further reduced for as much as 28%.


Artificial neural network Location Positioning Radio Space partitioning WLAN 


  1. 1.
    Gu Y, Lo A, Niemegeers I (2009) A survey of indoor positioning systems for wireless personal networks. IEEE Commun Surv Tutor 11(1):13–32CrossRefGoogle Scholar
  2. 2.
    van Diggelen F (2002) Indoor GPS theory & implementation. Position Location and Navigation Symposium, 2002 IEEE, pp 240–247Google Scholar
  3. 3.
    Ahonen S, Eskelinen P (2003) Mobile terminal location for UMTS. IEEE Aerosp Electro Syst Mag 18(2):23–27CrossRefGoogle Scholar
  4. 4.
    Llombart M, Ciurana M, Barcelo-Arroyo F (2008) On the scalability of a novel WLAN positioning system based on time of arrival measurements. 5th Workshop on Positioning, Navigation and Communication, 2008. WPNC 2008, pp 15–21Google Scholar
  5. 5.
    King T, Kopf S, Haenselmann T, Lubberger C, Effelsberg W (2006) COMPASS: a probabilistic indoor positioning system based on 802.11 and digital compasses. University of Mannheim, 68159 Mannheim, Germany, TR-2006-012Google Scholar
  6. 6.
    Sayrafian-Pour K, Kaspar D (2005) Indoor positioning using spatial power spectrum. IEEE PIMRC 4:2722–2726Google Scholar
  7. 7.
    Wang, H., Jia, F.: A Hybrid Modeling for WLAN Positioning System. International Conference on Wireless Communications, Networking and Mobile Computing, 2007. pp.2152 - 2155 (Sept. 2007)Google Scholar
  8. 8.
    Bahl P, Padmanabhan VN (2000) RADAR: an in-building RF-based user location and tracking system. INFOCOM 2:775–784Google Scholar
  9. 9.
    Li B, Salter J, Dempster A, Rizos C (2006) Indoor positioning techniques based on wireless LAN. AusWireless ’06, SydneyGoogle Scholar
  10. 10.
    Youssef M, Agrawala A (2005) The Horus WLAN location determination system. Int. Conf. on Mobile Systems, Applications and Services, pp 205–218Google Scholar
  11. 11.
    Eckert K (2005) Overview of wireless LAN based indoor positioning systems. Mobile Business Seminar, University of Mannheim, GermanyGoogle Scholar
  12. 12.
    Roos T, Myllymaki P, Tirri H (2002) A statistical modeling approach to location estimation. IEEE Trans Mob Comput 1(1):59–69CrossRefGoogle Scholar
  13. 13.
    Battiti R, Nhat TL, Villani A (2002) Location-aware computing: a neural network model for determining location in wireless LANs. Technical report # DIT-02-0083Google Scholar
  14. 14.
    Kaemarungsi K (2006) Distribution of WLAN received signal strength indication for indoor location determination. 1st International Symposium on Wireless Pervasive Computing, 2006, p 6Google Scholar
  15. 15.
    Youssef M, Agrawala A (2003) Small-scale compensation for WLAN location determination systems. Wirel Commun Netw 3(20–20):1974–1978Google Scholar
  16. 16.
    Youssef MA, Agrawala A, Shankar AU (2003) WLAN location determination via clustering and probability distributions. Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, pp 143–150Google Scholar
  17. 17.
    Ramachandran A, Jagannathan S (2007) Spatial diversity in signal strength based WLAN location determination systems. 32nd IEEE Conference on Local Computer Networks, 2007, pp 10–17Google Scholar
  18. 18.
    Ramachandran A, Jagannathan S (2007) Use of frequency diversity in signal strength based WLAN location determination systems. 32nd IEEE Conference on Local Computer Networks, 2007, pp 117–124Google Scholar
  19. 19.
    Li B, Wang Y, Lee HK, Dempster A, Rizos C (2005) Method for yielding a database of location fingerprints in WLAN. IEE Proc Commun 152(5):580–586CrossRefGoogle Scholar
  20. 20.
    Zhang M, Zhang S, Cao J (2008) Fusing received signal strength from multiple access points for WLAN user location estimation. International Conference on Internet Computing in Science and Engineering, 2008, pp 173–180Google Scholar
  21. 21.
    Hanson SJ, Burr DJ (1988) Minkowski-r backpropagation: learning in connectionist models with non-Euclidean error signals. In: Anderson DZ (ed) Neural information processing systems (Denver, 1987). American Institute of Physics, New York, pp 348–357Google Scholar
  22. 22.
    Hasoun HM (1995) Fundamentals of artificial neural networks. MIT, Cambridge, MAGoogle Scholar
  23. 23.
    Fahlman S, Lebiere C (1990) The cascade-correlation learning architecture. Adv Neural Inf Process Syst 2:524–532Google Scholar
  24. 24.
    Shang Y, Wah WB (1996) Global optimization for neural network training. IEEE Comput 29:45–56Google Scholar
  25. 25.
    Weisstein, EW (2003) Uniform difference distribution. From MathWorld—a Wolfram Web Resource. http://mathworld.wolfram.com/UniformDifferenceDistribution.html
  26. 26.
    Lin T-N, Lin P-C (2005) Performance comparison of indoor positioning techniques based on location fingerprinting in wireless networks. International Conference on Wireless Networks, Communications and Mobile Computing, vol 2, pp 1569–1574Google Scholar

Copyright information

© Institut TELECOM and Springer-Verlag 2009

Authors and Affiliations

  • Miloš N. Borenović
    • 1
    • 2
  • Aleksandar M. Nešković
    • 1
  1. 1.School of Electrical EngineeringUniversity of BelgradeBelgradeSerbia
  2. 2.WCRG, School of InformaticsUniversity of WestminsterLondonUK

Personalised recommendations