An Original Approach to Positioning with Cellular Fingerprints Based on Decision Tree Ensembles

  • Andrea VielEmail author
  • Andrea Brunello
  • Angelo Montanari
  • Federico Pittino
Conference paper
Part of the Lecture Notes in Geoinformation and Cartography book series (LNGC)


In addition to being a fundamental infrastructure for communication, cellular networks are employed for positioning through signal fingerprinting. In this respect, the choice of the specific strategy used to obtain a position estimation from fingerprints plays a major role in determining the overall accuracy. In this paper, a new machine learning approach, based on decision tree ensembles, is outlined and evaluated against a set of well-known, state-of-the-art fingerprint comparison functions from the literature. Tests are carried out with different tracking devices and environmental settings. It turns out that the proposed approach provides consistently better estimations than the other considered functions.


Positioning Fingerprinting Cellular Machine learning Random forest 


  1. Bahl P, Padmanabhan VN (2000) Radar: an in-building RF-based user location and tracking system. In: Proceedings of of the 19th INFOCOM, vol 2. IEEE, pp 775–784Google Scholar
  2. Bozkurt S, Elibol G, Gunal S, Yayan U (2015) A comparative study on machine learning algorithms for indoor positioning. In: International symposium on innovations in intelligent SysTems and applications (INISTA), pp 1–8.
  3. Caffery J, Stuber GL (1998) Subscriber location in CDMA cellular networks. IEEE Trans Veh Technol 47(2):406–416CrossRefGoogle Scholar
  4. Chen MY, Sohn T, Chmelev D, Haehnel D, Hightower J, Hughes J, LaMarca A, Potter F, Smith I, Varshavsky A (2006) Practical metropolitan-scale positioning for GSM phones. In: Proceedings of the 8th UbiComp. Springer, pp 225–242Google Scholar
  5. Deblauwe N (2008) GSM-based positioning: techniques and applications. ASPGoogle Scholar
  6. Deligiannis N, Louvros S, Kotsopoulos S (2007) Mobile positioning based on existing signalling messages in GSM networks. In: Proceedings of the 3rd MOBIMEDIAGoogle Scholar
  7. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. SIGKDD Explor Newsl 11(1):10–18.
  8. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference and prediction, 2nd edn. SpringerGoogle Scholar
  9. Jedari E, Wu Z, Rashidzadeh R, Saif M (2015) Wi-fi based indoor location positioning employing random forest classifier. In: 2015 international conference on indoor positioning and indoor navigation (IPIN), pp 1–5.
  10. Kjrgaard MB, Munk CV (2008) Hyperbolic location fingerprinting: a calibration-free solution for handling differences in signal strength (concise contribution). In: 2008 Sixth annual IEEE international conference on pervasive computing and communications (PerCom), pp 110–116.
  11. Li X, Zhang X, Chen K, Feng S (2014) Measurement and analysis of energy consumption on android smartphones. In: Proceedings of the 4th ICIST. IEEE, pp 242–245.
  12. Meniem MHA, Hamad AM, Shaaban E (2013) Relative RSS-based GSM localization technique. In: IEEE international conference on electro-information technology, EIT 2013, pp 1–6.
  13. Ngai EWT, Hu Y, Wong YH, Chen Y, Sun X (2011) The application of data mining techniques in financial fraud detection: a classification framework and an academic review of literature. Decis Support Syst 50(3):559–569.
  14. Paek J, Kim KH, Singh JP, Govindan R (2011) Energy-efficient positioning for smartphones using cell-id sequence matching. In: Proceedings of the 9th MobiSys. ACM, pp 293–306Google Scholar
  15. PostgreSQL Global Development Group (2008) PostgreSQL.
  16. Qi Y, Kobayashi H, Suda H (2006) Analysis of wireless geolocation in a non-line-of-sight environment. IEEE Trans Wirel Commun 5(3):672–681CrossRefGoogle Scholar
  17. Retscher G, Joksch J (2016) Comparison of different vector distance measure calculation variants for indoor location fingerprinting. In: Proceedings of the 13th international conference on location-based services, ICA, pp 53–76Google Scholar
  18. Romero C, Ventura S (2010) Educational data mining: a review of the state of the art. IEEE Trans Syst Man Cybern Part C 40(6):601–618.
  19. Sánchez D, Quinteiro JM, Hernández-Morera P, Martel-Jordán E (2012) Using data mining and fingerprinting extension with device orientation information for WLAN efficient indoor location estimation. In: 2012 IEEE 8th international conference on wireless and mobile computing, networking and communications (WiMob). IEEE, pp 77–83Google Scholar
  20. Sohn T, Varshavsky A, LaMarca A, Chen MY, Choudhury T, Smith I, Consolvo S, Hightower J, Griswold WG, de Lara E (2006) Mobility detection using everyday GSM traces. Springer, Berlin, Heidelberg, pp 212–224. Google Scholar
  21. Spirito MA, Mattioli AG (1998) On the hyperbolic positioning of GSM mobile stations. In: Proceedings of ISSSE ’98. IEEE, pp 173–177Google Scholar
  22. Tomar D, Agarwal S (2013) A survey on data mining approaches for healthcare. Int J Bio-Sci Bio-Technol 5(5):241–266CrossRefGoogle Scholar
  23. Witten IH, Frank E, Hall MA (2011) Data mining: practical machine learning tools and techniques, 3rd edn. Morgan Kaufmann Publishers Inc., San Francisco, CA, USAGoogle Scholar
  24. Zekavat R, Buehrer RM (2011) Handbook of position location: theory, practice and advances, 1st edn. Wiley-IEEE PressGoogle Scholar
  25. Zhuang Z, Kim KH, Singh JP (2010) Improving energy efficiency of location sensing on smartphones. In: Proceedings of the 8th MobiSys. ACM, pp 315–330Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Andrea Viel
    • 1
    Email author
  • Andrea Brunello
    • 1
  • Angelo Montanari
    • 1
  • Federico Pittino
    • 2
  1. 1.University of UdineUdineItaly
  2. 2.u-blox Italia SpATriesteItaly

Personalised recommendations