Machine Learning-Based Real-Time Indoor Landmark Localization

  • Zhongliang ZhaoEmail author
  • Jose Carrera
  • Joel Niklaus
  • Torsten Braun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10866)


Nowadays, smartphones can collect huge amounts of data from their surroundings with the help of highly accurate sensors. Since the combination of the Received Signal Strengths of surrounding access points and sensor data is assumed to be unique in some locations, it is possible to use this information to accurately predict smartphones’ indoor locations. In this work, we apply machine learning methods to derive the correlation between smartphones’ locations and the received Wi-Fi signal strength and sensor values. We have developed an Android application that is able to distinguish between rooms on a floor, and special landmarks within the detected room. Our real-world experiment results show that the Voting ensemble predictor outperforms individual machine learning algorithms and it achieves the best indoor landmark localization accuracy of 94% in office-like environments. This work provides a coarse-grained indoor room recognition and landmark localization within rooms, which can be envisioned as a basis for accurate indoor positioning.


Machine learning Indoor localization Real-time landmark detection 



This work was supported by the Swiss National Science Foundation #154458.


  1. 1.
    He, S., Chan, S.: Wi-Fi fingerprint-based indoor positioning: recent advances and comparisons. IEEE Commun. Surv. Tutor. 18, 466–490 (2016)CrossRefGoogle Scholar
  2. 2.
    Ouyang, R.W., Wong, A.K.S., Lea, C.T., Chiang, M.: Indoor location estimation with reduced calibration exploiting unlabeled data via hybrid generative/discriminative learning. IEEE Trans. Mob. Comput. 11, 1613–1626 (2012)CrossRefGoogle Scholar
  3. 3.
    Lakmali, B., Wijesinghe, W., de SIva, K., Liyanagama, K., Dias, S.: Design, implementation & testing of positioning techniques in mobile networks. In: The 3rd International Conference on Information and Automation for SustainabilityGoogle Scholar
  4. 4.
    Ghahramani, Z.: An introduction to hidden Markov models and Bayesian networks. Int. J. Pattern Recognit. Artif. Intell. 15, 9–42 (2001)CrossRefGoogle Scholar
  5. 5.
    Bousquet, O., von Luxburg, U., Ratsch, G.: Bayesian inference: an introduction to principles and practice in machine learning. Fresenius Environ. Bull. 20(5) (2004)Google Scholar
  6. 6.
    Ferris, B., Hahnel, D., Fox, D.: Gaussian processes for signal strength-based location estimation. In: Procedures of Robotics Science and Systems (2006)Google Scholar
  7. 7.
    Chai, X., Yang, Q.: Reducing the calibration effort for probabilistic indoor location estimation. IEEE Trans. Mob. Comput. 6(6), 649–662 (2016)CrossRefGoogle Scholar
  8. 8.
    Madigan, D., Einahrawy, E., Martin, R.,Ju, W., krishnan, P., Krishnakumar, A.:Bayesian indoor positioning systems. In: IEEE INFOCOM, vol. 2, pp. 1217–1227 (2005)Google Scholar
  9. 9.
    Liu, S., Luo, H., Zou, S.: A low-cost and accurate indoor localization algorithm using label propagation based semi supervised learning. In: Fifth International Conference Mobile Ad-Hoc and Sensor Networks, pp. 108–111 (2009)Google Scholar
  10. 10.
    Mascharka, D., Manley, E.: LIPS: learning based indoor positioning system using mobile phone-based sensors. In: 2016 13th IEEE Annual Consumer Communications and Networking Conference (CCNC), Las Vegas, NV, pp. 968–971 (2016)Google Scholar
  11. 11.
    Carrera, J., Zhao, Z., Braun, T., Li, Z., Neto, A.: A real-time robust indoor tracking system in smartphones. J. Comput. Commun. Scholar

Copyright information

© IFIP International Federation for Information Processing 2018

Authors and Affiliations

  • Zhongliang Zhao
    • 1
    Email author
  • Jose Carrera
    • 1
  • Joel Niklaus
    • 1
  • Torsten Braun
    • 1
  1. 1.Institute of Computer ScienceUniversity of BernBernSwitzerland

Personalised recommendations