Robust positioning system based on fingerprint approach

ABSTRACT

With growth of world wide cellular connections, localization within cellular network will play a central role in enabling value-added services. This is a huge revenue opportunity for mobile operators. Existing location techniques have poor performance in urban and indoor environments due to severe multipath and NLOS propagations, which are significant for those areas. Fingerprint-based methods have been preferred for those types of environments. In this work, a fingerprint-based technique is developed and applied. RSSI data used during training phase of the pattern-matching system are generated from the so-called in this work Thomas Kuerner propagation model. Moreover, motion detection algorithm and discrimination algorithm between indoor and outdoor environments are developed and could be used to further improve the positioning accuracy of a fingerprint-based positioning system. Tracking algorithm adapted to the fingerprint-based approach is developed and implemented. As result, a robust positioning system is achieved.

REFERENCES

• 1: C. Nerguizian, C. Despins, and S. Affes, "Indoor Geolocation with received Signal Strengths Fingerprinting Technique and Neural Networks," presented at ICT, Putten, 2004.
• 2: J. Kriegl, "Location in cellular networks," Diploma Thesis, Institute for Applied Information Processing and Communications, University of Technology Graz, Austria 2000.
• 3: Kamol Kaemarungsi , Prashant Krishnamurthy, Design of indoor positioning systems based on location fingerprinting technique, University of Pittsburgh, Pittsburgh, PA, 2005
• 4: C. M. Takenga and K. Kyamakya, "Pre-processing of Data in RSS Signature-based Localization," presented at Workshop on Positioning, Navigation and Communications (WPNC), Hannover, Germany, 2006.
• 5: SnapTrack, "Location Technologies for GSM, GPRS and UMTS Networks," Qualcomm Company, http://www.cdmatech.com/download_library/pdf/location_tech_wp_1--03.pdf, 20.05.2007.
• 6: G. Wilde, "Performance implications of wireless location technologies-effect on location-based services revenue growth," in Business Briefing: Wireless Technology, 2003, pp. 1--4.
• 7: T. Kurner and A. Meier, "Prediction of outdoor and outdoor-to-indoor coverage in urban areas at 1.8GHz," IEEE Trans. on Selected Areas in Communications., vol. 20, pp. 496--506, 2002.
• 8: C. Takenga, X. Chen, and K. Kyamakya, "Fusion of Neural Network positioning and Database Correlation in localizing a Mobile Terminal," presented at International Conference on Wireless Networks (ICWN), Las Vegas, USA, 2006.
• 9: Gérard Dreyfus, Neural Networks, Springer-Verlag New York, Inc., Secaucus, NJ, 2005
• 10: Christopher M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, Inc., New York, NY, 1995
• 11: R. Reed, "Pruning algorithms -- a survey," IEEE Trans. on Neural Networks, vol. 4(5), pp. 740--747, 1991.
• 12: K. Messer and J. Kittler, "Choosing an optimal neural network size to aid search through a large image database," presented at British Machine Vision Conference (BMVC), Southampton, UK, 1998.
• 13: D. Patterson, Artificial Neural Network. Singapore: Prentice Hall, 1996.
• 14: E. Vonk , L. C. Jain , R. P. Johnson, Automatic Generation of Neural Network Architecture Using Evolutionary Computation, World Scientific Publishing Co., Inc., River Edge, NJ, 1997
• 15: Cornelius T. Leondes, Algorithms and Architectures, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1997
• 16: I. Anderson and H. Muller, "Context Awareness via GSM Signal Strength Fluctuation," presented at International Conference on Pervasive Computing, Dublin, Ireland, 2006.
• 17: F. Erbas, J. Steuer, K. Kyamakya, D. Eggesieker, and K. Jobmann, "Regular Path Recognition Method and. Prediction of User Movements in Wireless Networks," presented at Vehicular Technology Conference (VTC-Fall), New Jersey, USA, 2001.
• 18: E. Brookner, Tracking and Kalman filtering made easy. New York: John Wiley & Sons, 1998.
• 19: Yaakov Bar-Shalom , Xiao-Rong Li, Estimation with Applications to Tracking and Navigation, John Wiley & Sons, Inc., New York, NY, 2001
• 20: C. Takenga, T. Peng, and K. Kyamakya, "Post--processing of Fingerprint Localization using Kalman Filter and Map--Matching Techniques," presented at International Conference on Advanced Communication Technologies (ICACT), Seoul, Korea, 2007.

INDEX TERMS

Primary Classification:
  B. Hardware
  B.4 INPUT/OUTPUT AND DATA COMMUNICATIONS
      B.4.m Miscellaneous

Additional Classification:
  H. Information Systems
  H.0 GENERAL

General Terms:
Algorithms, Experimentation, Measurement, Performance, Reliability

Keywords:
GSM localization, fingerprint positioning, neural networks, tracking