Deep Feature Extraction from Trajectories for Transportation Mode Estimation

  • Yuki EndoEmail author
  • Hiroyuki Toda
  • Kyosuke Nishida
  • Akihisa Kawanobe
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9652)


This paper addresses the problem of feature extraction for estimating users’ transportation modes from their movement trajectories. Previous studies have adopted supervised learning approaches and used engineers’ skills to find effective features for accurate estimation. However, such hand-crafted features cannot always work well because human behaviors are diverse and trajectories include noise due to measurement error. To compensate for the shortcomings of hand-crafted features, we propose a method that automatically extracts additional features using a deep neural network (DNN). In order that a DNN can easily handle input trajectories, our method converts a raw trajectory data structure into an image data structure while maintaining effective spatio-temporal information. A classification model is constructed in a supervised manner using both of the deep features and hand-crafted features. We demonstrate the effectiveness of the proposed method through several experiments using two real datasets, such as accuracy comparisons with previous methods and feature visualization.


Movement trajectory Deep learning Transportation mode 


  1. 1.
    Arel, I., Rose, D.C., Karnowski, T.P.: Deep machine learning - a new Frontier in artificial intelligence research. IEEE Comput. Int. Mag. 5(4), 13–18 (2010)CrossRefGoogle Scholar
  2. 2.
    Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: NIPS, pp. 153–160 (2006)Google Scholar
  3. 3.
    Bengio, Y.: Learning deep architectures for AI. FTML 2(1), 1–127 (2009)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. TASLP 20(1), 30–42 (2012)Google Scholar
  5. 5.
    Ermes, M., Parkka, J., Mantyjarvi, J., Korhonen, I.: Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE Trans. Inform. Tech. Biomed. 12(1), 20–26 (2006)CrossRefGoogle Scholar
  6. 6.
    Hinton, G.E., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Hung, C.-C., Peng, W.C., Lee, W.C.: Clustering and aggregating clues of trajectories for mining trajectory patterns and routes. VLDB J. 24(2), 169–192 (2015)CrossRefGoogle Scholar
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NIPS. pp. 1106–1114 (2012)Google Scholar
  9. 9.
    Le, Q.V., Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Ng, A.Y.: On optimization methods for deep learning. In: ICML, pp. 265–272 (2011)Google Scholar
  10. 10.
    Liao, L., Fox, D., Kautz, H.: Learning and inferring transportation routines. In: AAAI 2004, pp. 348–353 (2004)Google Scholar
  11. 11.
    Parker, J.A., Kenyon, R.V., Troxel, D.: Comparison of interpolating methods for image resampling. IEEE Trans. Med. Imaging 2(1), 31–39 (1983)CrossRefGoogle Scholar
  12. 12.
    Parkka, J., Ermes, M., Korpippa, P., Mantyjarvi, J., Peltola, J.: Activity classification using realistic data from wearable sensors. IEEE Trans. Inform. Technol. Biomed. 10(1), 119–128 (2006)CrossRefGoogle Scholar
  13. 13.
    Patterson, D., Liao, L., Fox, D., Kautz, H.: Inferring high-level behavior from low-level sensors. In: UbiComp, pp. 73–89 (2003)Google Scholar
  14. 14.
    Shah, R.C., Wan, C.-Y., Lu, H., Nachman, L.: Classifying the mode of transportation on mobile phones using GIS information. In: UbiComp, pp. 225–229 (2014)Google Scholar
  15. 15.
    Shaw, B., Shea, J., Sinha, S., Hogue, A.: Learning to rank for spatiotemporal search. In: WSDM, pp. 717–726 (2013)Google Scholar
  16. 16.
    Song, X., Zhang, Q., Sekimoto, Y., Shibasaki, R.: Prediction of human emergency behavior and their mobility following large-scale disaster. In: KDD, pp. 5–14 (2014)Google Scholar
  17. 17.
    Toda, H., Yasuda, N., Matsuura, Y., Kataoka, R.: Geographic information retrieval to suit immediate surroundings. In: GIS, pp. 452–455 (2009)Google Scholar
  18. 18.
    Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms. In: MM. pp. 1469–1472 (2010)Google Scholar
  19. 19.
    Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. JMLR 11, 3371–3408 (2010)MathSciNetzbMATHGoogle Scholar
  20. 20.
    Zheng, Y.: Trajectory data mining: an overview. ACM TIST 6(3), 29 (2015)Google Scholar
  21. 21.
    Zheng, Y., Liu, L., Wang, L., Xie, X.: Learning transportation mode from raw GPS data for geographic applications on the web. In: WWW, pp. 247–256 (2008)Google Scholar
  22. 22.
    Zheng, Y., Li, Q., Chen, Y., Xie, X., Ma, W.-Y.: Understanding mobility based on GPS data. In: Ubicomp, pp. 312–321 (2008)Google Scholar
  23. 23.
    Zheng, Y., Chen, Y., Li, Q., Xie, X., Ma, W.-Y.: Understanding transportation modes based on GPS data for web applications. TWEB. 4(1), 1 (2010)CrossRefGoogle Scholar
  24. 24.
    Zheng, Y., Zhou, X. (eds.): Computing with Spatial Trajectories. Springer, New York (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Yuki Endo
    • 1
    Email author
  • Hiroyuki Toda
    • 1
  • Kyosuke Nishida
    • 1
  • Akihisa Kawanobe
    • 1
  1. 1.NTT Service Evolution LaboratoriesYokosukaJapan

Personalised recommendations