Identifying Mobility of Drug Addicts with Multilevel Spatial-Temporal Convolutional Neural Network

  • Canghong JinEmail author
  • Haoqiang Liang
  • Dongkai Chen
  • Zhiwei Lin
  • Minghui Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11439)


Human identification according to their mobility patterns is of great importance for a wide spectrum of spatial-temporal based applications. For example, detecting drug addicts from normal residents in public security area. However, extracting and classifying user behaviors in massive amount of moving records is not trivial because of three challenges: (1) the complex transition records with noisy data; (2) the heterogeneity and sparsity of spatiotemporal trajectory features; and (3) extremely imbalanced data distribution of real world data. In this paper, we propose MST-CNN, a multi-level convolutional neural network with spatial and temporal features. We first embed the multiple factors on single trajectory level and then generate a behavior matrix to capture the user’s mobility patterns. Finally, a CNN module is used to extract various features with different filters and classify user type. We perform experiments on real-life mobility datasets provided by public security office, and extensive evaluation results demonstrate that our method obtains significant improvement performance in identification accuracy and outperform all baseline methods.


Convolutional neural network Spatiotemporal embedding Human trajectory pattern Addict identification 


  1. 1.
  2. 2.
  3. 3.
    Zhonghua, S.U., et al.: A longitudinal survey of patterns and prevalence on addictive drug use in general population in five or six areas with high-prevalence in china from 1993 to 2000 part three: demographic characteristics of illicit drug users. Chinese J. Drug Depend. (2005)Google Scholar
  4. 4.
    Yan, W., Jiang, W.W., Zhang, D.S.: A study on drug-taking behavior based on big data: taking Guizhou province as an example. J. Shandong Police Coll. (2017)Google Scholar
  5. 5.
  6. 6.
    Du, B., Liu, C., Zhou, W., et al.: Catch me if you can: detecting pickpocket suspects from large-scale transit records. In: SIGKDD (2016)Google Scholar
  7. 7.
    Gong, H., Chen, C., Bialostozky, E., et al.: A GPS/GIS method for travel mode detection in New York City. Comput. Environ. Urban Syst. 36(2), 131–139 (2012)CrossRefGoogle Scholar
  8. 8.
    Pinelli, F., Pinelli, F., Pinelli, F., et al.: Trajectory pattern mining. In: SIGKDD (2007)Google Scholar
  9. 9.
    Laube, P., Imfeld, S.: Analyzing relative motion within groups oftrackable moving point objects. In: Egenhofer, M.J., Mark, D.M. (eds.) GIScience 2002. LNCS, vol. 2478, pp. 132–144. Springer, Heidelberg (2002). Scholar
  10. 10.
    Li, M., Ahmed, A., Smola A.J.: Inferring movement trajectories from GPS snippets. In: WSDM (2015)Google Scholar
  11. 11.
    Chen, C., Zhang, D., Zhou, Z-H., Li, N., Atmaca, T., Li, S.: B-planner: night bus route planning using large-scale taxi GPS traces. In: PerCom (2013)Google Scholar
  12. 12.
    Luo, W., Tan, H., Chen, L., Ni, L.M.: Finding time period-based most frequent path in big trajectory data. In: SIGMOD (2013)Google Scholar
  13. 13.
    Coelho da Silva, T.L., de Macêdo, J.A.F., Casanova, M.A.: Discovering frequent mobility pat-terns on moving object data. In: MobiGIS (2014)Google Scholar
  14. 14.
    Jing, Y., Zheng, Y., Xie, X.: Discovering regions of different functions in a city using human mobility and pois. In: KDD (2012)Google Scholar
  15. 15.
    Li, Q., Zheng, Y., Xie, X., et al.: Mining user similarity based on location history. In: SIGSPATIAL (2008)Google Scholar
  16. 16.
    Ying, J.C., Lu, H.C., Lee, W.C., et al.: Mining user similarity from semantic trajectories. In: SIGSPATIAL (2010)Google Scholar
  17. 17.
    Abul, O., Bonchi, F., Nanni, M.: Anonymization of moving objects databases by clustering and perturbation. Inf. Syst. 35(8), 884–910 (2010)CrossRefGoogle Scholar
  18. 18.
    Zhang, C., Zhang, K., Yuan, Q., et al.: GMove: group-level mobility modeling using geo-tagged social media. In: SIGKDD (2016)Google Scholar
  19. 19.
    Zhang, J., Zheng, Y., Qi, D.: Deep spatio-temporal residual networks for citywide crowd flows prediction. In: AAAI (2017)Google Scholar
  20. 20.
    Feng, J., et al.: DeepMove: predicting human mobility with attentional recurrent networks. In: WWW (2018)Google Scholar
  21. 21.
    Kong, D., Wu, F.: HST-LSTM: a hierarchical spatial-temporal long-short term memory network for location prediction. In: IJCAI (2018)Google Scholar
  22. 22.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)Google Scholar
  23. 23.
    Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882, (2014)
  24. 24.
    Vaswani, A., et. al.: Attention is all you need. arXiv:1706.03762

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Canghong Jin
    • 1
    Email author
  • Haoqiang Liang
    • 2
  • Dongkai Chen
    • 1
  • Zhiwei Lin
    • 2
  • Minghui Wu
    • 1
  1. 1.Zhejiang University City CollegeHangzhouChina
  2. 2.Zhejiang UniversityHangzhouChina

Personalised recommendations