MOBILITY EMBEDDING FROM CALL DATA RECORD USING WORD2VEC TO SUPPORT NETWORK WITH UNMANNED AERIAL VEHICLE
https://doi.org/10.55452/1998-6688-2023-20-1-45-53
Abstract
Call Detail Records (CDRs) are records that provide information about phone conversations and text messages. CDR data has been proved in several studies to give useful information on people's mobility patterns and associations with fine-grained temporal and geographical characteristics. This paper proposes to embed the traces recorded in the CDRs to extract meaningful information. These latter provide insights about the location that may need support to cover or recover the network. After embedding the users' trajectories step, we use the embedding results to recommend the antennas with coordinates and support demand needed to a fleet of Unmanned Aerial Vehicle. Finally, we ended up with a capacitated vehicle routing problem that we solved using a Google open-source software named OR-Tools.
About the Authors
Imed Eddine Semassel
El Manar University
Tunisia
Tunisia
Imed Eddine Semassel, PhD student, Department of Computer Science, Faculty of Sciences of Tunis
Sadok Ben Yahia
Tallinn Univeristy of Technology
Estonia
Estonia
Sadok Ben Yahia, Professor
Tallinn
References
1. Association C. T. (2017, July). How mobile phones are changing the developing world. Retrieved from https://www.cta.tech/News/Blog/Articles/2015/July/How-Mobile-Phones-Are-Changing-the-Developing-Worl.aspx.
2. Bianchi F. M., Scardapane, S., Uncini, A., Rizzi, A., & Sadeghian, A. (2015). Prediction of telephone calls load using Echo State Network with exogenous variables. Neural Networks, 71, 204–213. https://doi.org/https://doi.org/10.1016/j.neunet.2015.08.010.
3. Bradley P.S., Bennett K.P. & Demiriz A. (2000). Constrained k-means clustering. Microsoft Research, Redmond, 20(0), 0.
4. Crivellari A. & Beinat E. (2019). From motion activity to geo-embeddings: Generating and exploring vector representations of locations, traces and visitors through large-scale mobility data. ISPRS International Journal of Geo-Information, 8(3), 134.
5. Cuzzocrea A., Ferri F. & Grifoni P. (2018). Intelligent Sensor Data Fusion for Supporting Advanced Smart Health Processes. In L. Barolli & O. Terzo (Eds.), Complex, Intelligent, and Software Intensive Systems (Vol. 611, pp. 361–370). https://doi.org/10.1007/978-3-319-61566-0_33
6. OR-tools. Retrieved from https://developers.google.com/optimization
7. Gore R., Wozny P., Dignum F. P. M., Shults F. L. van Burken C. B. & Royakkers, L. (2019). A Value Sensitive ABM of the Refugee Crisis in the Netherlands. Proceeding 2019 Spring Simulation Conference (SpringSim), 1–12.
8. Louail T., Lenormand M., Ros O.G. C., Picornell M., Herranz R., Frias-Martinez E., … Barthelemy M. (2015). From mobile phone data to the spatial structure of cities. Scientific Reports, 4. https://doi.org/https://doi.org/10.1038/srep05276.
9. Mikolov T., Chen K., Corrado G. & Dean J. (2013). Efficient estimation of word representations in vector space. ArXiv Preprint ArXiv:1301.3781.
10. Mobile policy handbook: an insider’s guide to the issues. (2017). Retrieved from https://www.gsma.com/mena/wp-content/uploads/2018/10/Mobile_Policy_Handbook_2017_EN.pdf
11. Solomon A., Bar A., Yanai C., Shapira B. & Rokach, L. (2018). Predict demographic information using word2vec on spatial trajectories. Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization, 331–339.
12. Tian C., Zhang Y. & Weng Z. (2021). Learning Large-scale Location Embedding From Human Mobility Trajectories with Graphs. CoRR, abs/2103.00483. Retrieved from https://arxiv.org/abs/2103.00483
13. Zhou N., Zhao W. X., Zhang X., Wen J.-R. & Wang S. (2016). A general multi-context embedding model for mining human trajectory data. IEEE Transactions on Knowledge and Data Engineering, 28(8), 1945–1958.
14. Zhu M., Chen W., Xia J., Ma Y., Zhang Y., Luo Y. … Liu L. (2019). Location2vec: a situation-aware representation for visual exploration of urban locations. IEEE Transactions on Intelligent Transportation Systems, 20(10), 3981–3990.
Review
For citations:
Semassel I.E., Ben Yahia S. MOBILITY EMBEDDING FROM CALL DATA RECORD USING WORD2VEC TO SUPPORT NETWORK WITH UNMANNED AERIAL VEHICLE. Herald of the Kazakh-British technical university. 2023;20(1):45-53. https://doi.org/10.55452/1998-6688-2023-20-1-45-53
Views:
338
Email this article 