Applying Artificial Neural Networks on Two-Layer Semantic Trajectories for Predicting the Next Semantic Location

  • Antonios KaratzoglouEmail author
  • Harun Sentürk
  • Adrian Jablonski
  • Michael Beigl
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10614)


Location-awareness and prediction play a steadily increasing role as systems and services become more intelligent. At the same time semantics gain in importance in geolocation application. In this work, we investigate the use of artificial neural networks (ANNs) in the field of semantic location prediction. We evaluate three different ANN types: FFNN, RNN and LSTM on two different data sets on two different semantic levels each. In addition we compare each of them to a Markov model predictor. We show that neural networks perform overall well, with LSTM achieving the highest average score of 76,1%.


Feed-forward-, Recurrent-, LSTM- Artificial Neural Networks Markov chains Semantic trajectories Location prediction 


  1. 1.
    Alvares, L.O., Bogorny, V., Kuijpers, B., Moelans, B., Fern, J.A., Macedo, E., Palma, A.T.: Towards semantic trajectory knowledge discovery. In: Data Mining and Knowledge Discovery (2007)Google Scholar
  2. 2.
    Biesterfeld, J., Ennigrou, E., Jobmann, K.: Neural networks for location prediction in mobile networks. In: Proceedings of International Workshop on Applications of Neural Networks to Telecommunications, pp. 207–214 (1997)Google Scholar
  3. 3.
    Eagle, N., Pentland, A.S.: Reality mining: sensing complex social systems. Pers. Ubiquit. Comput. 10(4), 255–268 (2006)CrossRefGoogle Scholar
  4. 4.
    Etter, V., Kafsi, M., Kazemi, E.: Been there, done that: what your mobility traces reveal about your behavior. In: Proceedings of MDC by Nokia Workshop 10th PerCom (2012)Google Scholar
  5. 5.
    Song, X., Kanasugi, H., Shibasaki, R.: Deeptransport: prediction and simulation of human mobility and transportation mode at a citywide level. In: Proceedings of 25th International Joint Conference on Artificial Intelligence, pp. 2618–2624 (2016)Google Scholar
  6. 6.
    Spaccapietra, S., Parent, C., Damiani, M.L., de Macedo, J.A., Porto, F., Vangenot, C.: A conceptual view on trajectories. Data Knowl. Eng. 65(1), 126–146 (2008)CrossRefGoogle Scholar
  7. 7.
    Vintan, L., Gellert, A., Petzold, J., Ungerer, T.: Person movement prediction using neural nets. In: 1st Workshop on Modeling and Retrieval of Context, vol. 114, pp. 1–12 (2004)Google Scholar
  8. 8.
    Yan, Z., Chakraborty, D., Parent, C., Spaccapietra, S., Aberer, K.: Semantic trajectories: mobility data computation and annotation. ACM Trans. Intell. Syst. Technol. 4(3), 49:1–49:38 (2013)CrossRefGoogle Scholar
  9. 9.
    Ying, J.J.C., Lee, W.C., Weng, T.C., Tseng, V.S.: Semantic trajectory mining for location prediction. In: Proceedings of 19th ACM SIGSPATIAL, GIS 2011, pp. 34–43 (2011)Google Scholar
  10. 10.
    Zheng, Y., Zhang, L., Xie, X., Ma, W.Y.: Mining interesting locations and travel sequences from GPS trajectories. In: Proceedings of 18th International Conference on WWW, pp. 791–800 (2009)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Antonios Karatzoglou
    • 1
    • 2
    Email author
  • Harun Sentürk
    • 1
  • Adrian Jablonski
    • 1
  • Michael Beigl
    • 1
  1. 1.Karlsruhe Institute of TechnologyKarlsruheGermany
  2. 2.Robert Bosch GmbH, Corporate Sector Research and Advance EngineeringStuttgartGermany

Personalised recommendations