DOI QR코드

DOI QR Code

Estimating People's Position Using Matrix Decomposition

  • Dao, Thi-Nga (Department of Electrical and Computer Engineering, University of Ulsan) ;
  • Yoon, Seokhoon (Department of Electrical and Computer Engineering, University of Ulsan)
  • Received : 2019.03.13
  • Accepted : 2019.03.26
  • Published : 2019.06.30

Abstract

Human mobility estimation plays a key factor in a lot of promising applications including location-based recommendation systems, urban planning, and disease outbreak control. We study the human mobility estimation problem in the case where recent locations of a person-of-interest are unknown. Since matrix decomposition is used to perform latent semantic analysis of multi-dimensional data, we propose a human location estimation algorithm based on matrix factorization to reconstruct the human movement patterns through the use of information of persons with correlated movements. Specifically, the optimization problem which minimizes the difference between the reconstructed and actual movement data is first formulated. Then, the gradient descent algorithm is applied to adjust parameters which contribute to reconstructed mobility data. The experiment results show that the proposed framework can be used for the prediction of human location and achieves higher predictive accuracy than a baseline model.

Keywords

OTNBCL_2019_v8n2_39_f0001.png 이미지

Figure 1. Visual representation of latent factors of several users

OTNBCL_2019_v8n2_39_f0002.png 이미지

Figure 2. Location prediction framework

OTNBCL_2019_v8n2_39_f0003.png 이미지

Figure 3. Structure of matrix Mq for PCMs selection

OTNBCL_2019_v8n2_39_f0004.png 이미지

Figure 4. Matrix structure in the LEMD algorithm where each row of the matrix represents spatio-temporal data of person p at time t and PCMs at time t and (t - 1).

OTNBCL_2019_v8n2_39_f0005.png 이미지

Figure 5. Performance results of the proposed prediction framework on the MIT and Dartmouth datasets

References

  1. J. Feng, Y. Li, C. Zhang, F. Sun, F. Meng, A. Guo and D. Jin, "DeepMove: Predicting Human Mobility with Attentional Recurrent Networks," in Proceedings of the 2018 World Wide Web Conference (WWW '18), Lyon, France, 2018. DOI: https://doi.org/10.1145/3178876.3186058
  2. Y. Su, X. Li, W. Tang, J. Xiang and H. Yuanye, "Next Check-in Location Prediction via Footprints and Friendship on Location-Based Social Networks," in 19th IEEE International Conference on Mobile Data Management (MDM), Aalborg, Denmark, 2018. https://doi.org/10.1109/MDM.2018.00044
  3. H. Pang, P. Wang, L. Gao, M. Tang, J. Huang and L. Sun, "Crowdsourced mobility prediction based on spatiotemporal contexts," in 2016 IEEE International Conference on Communications (ICC), Kuala Lumpur, 2016. DOI: https://doi.org/10.1109/ICC.2016.7510707
  4. S. Hoteit, S. Secci, S. Sobolevsky, C. Ratti and G. Pujolle, "Estimating human trajectories and hotspots through mobile phone data," Computer Networks, vol. 64, pp. 296-307, 2014. DOI: https://doi.org/10.1016/j.comnet.2014.02.011
  5. G. Chen, A. C. Viana and M. Fiore, "Human Trajectory Recovery via Mobile Network Data," Roscoff, France, 2018.
  6. P. Symeonidis and A. Zioupos, Matrix and Tensor Factorization Techniques for Recommender Systems (1st ed.), Springer Publishing Company, 2017. DOI: https://doi.org/10.1007/978-3-319-41357-0
  7. N. E. a. A. Pentland, "Reality mining: sensing complex social systems," Personal Ubiquitous Computing, vol. 10, no. 4, pp. 255-268, 2006. DOI: https://doi.org/10.1007/s00779-005-0046-3
  8. D. Kotz, T. Henderson, L. Abyzov and J. Yeo, "CRAWDAD Dataset Dartmouth/campus (v. 2009-09-09)". DOI: https://doi.org/10.15783/C7F59T
  9. T.-N. Dao, D. V. Le and S. Yoon, "Predicting Human Location Using Correlated Movements," Electronics, vol. 8, no. 1, p. 54, 2019. DOI: https://doi.org/10.3390/electronics8010054
  10. C.-B. Nguyen, S. Yoon and Y. Kim, "Discovering Social Community Structures Based on Human Mobility Traces," Mobile Information Systems, vol. 2017, 2017. DOI: https://doi.org/10.1155/2017/2190310