Skip to main content

A Hybrid Machine Learning Based Low Cost Approach for Real Time Vehicle Position Estimation in a Smart City

  • Conference paper
  • First Online:
Advances in Ubiquitous Networking 2 (UNet 2016)

Part of the book series: Lecture Notes in Electrical Engineering ((LNEE,volume 397))

Included in the following conference series:


The Global Positioning System (GPS) enhanced with low cost Dead Reckoning (DR) sensors allows to estimate in real time a vehicle position with more accuracy while maintaining a low cost. The Extended Kalman Filter (EKF) is generally used to predict the position using the sensor’s measures and the GPS position as a helper. However, the filter performance tails off during periods of GPS failure and may quickly diverge (e.g., in tunnels or due to multipath phenomenon). In this paper, we propose a novel hybrid approach based on neural networks (NN) and autoregressive integrated moving average (ARIMA) models to circumvent the EKF limitations and improve the accuracy of vehicle position estimation. While GPS signals are available, we train NN and ARIMA models to learn the non-linear and linear structures in the vehicle position; therefore they can provide good predictions during GPS signal outages. We obtain empirically an improvement of up to 95 % over the simple EKF predictions in case of GPS failures.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions


  1. Nam, T., Pardo, T.A.: Conceptualizing smart city with dimensions of technology, people, and institutions. In: Proceedings of the 12th Annual International Digital Government Research Conference: Digital Government Innovation in Challenging Times, pp. 282–291. ACM, New York (2011)

    Google Scholar 

  2. Easton, R.D., Frazier, E.F.: GPS Declassified: From Smart Bombs to Smartphones. Potomac Books Inc., USA (2013)

    Google Scholar 

  3. Grewal, M.S., Weill, L.R., Andrews, A.P.: Global Positioning Systems, Inertial Navigation, and Integration. Wiley-Interscience, New York (2007)

    Book  Google Scholar 

  4. Zamora-Izquierdo, M.A., Betaille, D.F., Peyret, F., Joly, C.: Comparative study of Extended Kalman Filter, Linearised Kalman Filter and Particle Filter applied to low-cost GPS-based hybrid positioning system for land vehicles. In: International Journal of Intelligent Information and Database Systems, vol. 2, pp. 149–166. Inderscience Publishers, Geneva (2008)

    Google Scholar 

  5. Lucet, E., Betaille, D., Donnay Fleury, N., Ortiz, M., Salle, D., Canou, J.: Real-time 2D localization of a car-like mobile robot using dead reckoning and GPS, with satellite masking prediction. In: Accurate localization for land transportation Workshop, pp. 15–18. France (2009)

    Google Scholar 

  6. Chiang, K-W., Niu, X., El-Sheimy, N.: On the development of a conceptual intelligent navigator for a low cost DGPS/MEMS IMU integrated system. In: Proceedings of the 18th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2005), pp. 494–502. Long Beach, CA (2005)

    Google Scholar 

  7. Aggarwal, P., Syed, Z., El-Sheimy, N.: Hybrid Extended Particle Filter (HEPF) for integrated civilian navigation system. In: Position, Location and Navigation Symposium, 2008 IEEE/ION, pp. 984–992. IEEE, USA (2008)

    Google Scholar 

  8. Goodall, C.L.: Improving usability of low-cost INS/GPS navigation systems using intelligent techniques. Ph.D. dissertation, Department of Geomatics Engineering. Universiry of Calgary, Canada (2009)

    Google Scholar 

  9. Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting with artificial neural networks:: the state of the art. Int. J. Forecast. 14, 35–62 (1998). Elsevier Science B.V., USA

    Google Scholar 

  10. Chen, S.H., Hsu, C.W., Huang, S.H.: Recursive estimation of vehicle position by using navigation sensor fusion. In: 12th International Conference on ITS Telecommunications, pp. 532–536. IEEE, Taipei (2012)

    Google Scholar 

  11. Yashchenko, V.: Neural-like growing networks the artificial intelligence basic structure. In: Intelligent Systems in Science and Information 2014, pp. 41–55. Springer International Publishing (2014)

    Google Scholar 

  12. Khoi, D.D., Murayama, Y.: Multi-layer perceptron neural networks in geospatial analysis. In: Progress in Geospatial Analysis, pp. 125–141. Springer, Japan (2012)

    Google Scholar 

  13. Box, P., Jenkins, G.M.: Time Series Analysis: Forecasting and Control. Holden-day Inc., San Francisco (1976)

    MATH  Google Scholar 

  14. Korrapati, H., Courbon, J., Alizon, S., Marmoiton, F.: “The Institut Pascal Data Sets”: un jeu de données en extérieur, multicapteurs et datées avec réalité terrain, données d’étalonnage et outils logiciels. In: ORASIS 2013, Congrès des jeunes chercheurs en vision par ordinateur. France (2013)

    Google Scholar 

Download references


This work was financially supported by the National Center of Scientific and Technical Research (CNRST), Morocco.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Ikram Belhajem .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer Science+Business Media Singapore

About this paper

Cite this paper

Belhajem, I., Ben Maissa, Y., Tamtaoui, A. (2017). A Hybrid Machine Learning Based Low Cost Approach for Real Time Vehicle Position Estimation in a Smart City. In: El-Azouzi, R., Menasche, D.S., Sabir, E., De Pellegrini, F., Benjillali, M. (eds) Advances in Ubiquitous Networking 2. UNet 2016. Lecture Notes in Electrical Engineering, vol 397. Springer, Singapore.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-10-1626-4

  • Online ISBN: 978-981-10-1627-1

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics