TEMMUS: A Mobility Predictor based on Temporal Markov Model with User Similarity

• Felipe Araújo UFPA
• Denis Rosário UFPA
• Kássio Machado UFMG
• Eduardo Cerqueira UFPA
• Leandro Villas UNICAMP

DOI: https://doi.org/10.5753/sbrc.2019.7389

Resumo

Location-Based Social Networks (LBSN) data contains spatial, temporal, and social features of user activity, providing valuable information that is currently available on large-scale and low-cost fashion via traditional data collection methods. In this way, LBSN data enables to predict user mobility based on spatial, temporal, and social features, which can be used in several areas, such as, device-to-device(D2D) communication, cache, and others. In addition, a Temporal Markov Chain (TMC) is a stochastic model used to model randomly changing systems, such as mobility prediction based on the spatiotemporal factor such as location and day of the week. In this paper, we introduce the TEmporal Markov Model with User Similarity (TEMMUS) mobility prediction model. TEMMUS considers a TMC of variable order based on the day of the week (weekday or weekend) and the user similarity to predict the users future location. The results highlight a higher accuracy of TEMMUS compared to three state-of-the-art Markov Model predictors.

Palavras-chave: Redes Sociais Baseadas em Localização, Modelos de Mobilidade, Cadeias de Markov

Referências

Abani, N., Braun, T., and Gerla, M. (2017). Proactive caching with mobility prediction under uncertainty in information-centric networks. In Proceedings of the 4th ACM Conference on Information-Centric Networking, ICN 2017, Berlin, Germany, September 26-28, 2017, pages 88–97.

Chen, M., Liu, Y., and Yu, X. (2014). Nlpmm: A next location predictor with markov modeling. In Tseng, V. S., Ho, T. B., Zhou, Z.-H., Chen, A. L. P., and Kao, H.-Y., editors, Advances in Knowledge Discovery and Data Mining, pages 186–197, Cham. Springer International Publishing.

Cheng, C., Yang, H., King, I., and Lyu, M. R. (2012). Fused matrix factorization with geographical and social influence in location-based social networks. In Twenty-Sixth AAAI Conference on Artificial Intelligence, AAAI’12, pages 17–23. AAAI Press.

Gao, H. and Liu, H. (2015). Mining human mobile behavior with location-based social networks. Morgan & Claypool.

Gao, H., Tang, J., Hu, X., and Liu, H. (2013). Modeling temporal effects of human mobile behavior on location-based social networks. In 22nd ACM International Conference on Information & Knowledge Management, CIKM ’13, pages 1673–1678. ACM.

Jiang, J., Pan, C., Liu, H., and Yang, G. (2016). Predicting human mobility based on location data modeled by markov chains. Fourth International Conference on Ubiquitous Positioning, Indoor Navigation and Location Based Services (UPINLBS), pages 145–151.

Machado, K., Boukerche, A., Cerqueira, E., and Loureiro, A. A. (2016). Long-term spatiotemporal analysis of social media for device-to-device networks. In IEEE Global Communications Conference (GLOBECOM), pages 1–6. IEEE.

Machado, K., Boukerche, A., Cerqueira, E., and Loureiro, A. A. (2017). A socially-aware in-network caching framework for the next generation of wireless networks. IEEE Communications Magazine, 55(12):38–43.

Menz, L., Herberth, R., Luo, C., Gauterin, F., Gerlicher, A., and Wang, Q. (2018). An improved method for mobility prediction using a markov model and density estimation. In 2018 IEEE Wireless Communications and Networking Conference, WCNC 2018, Barcelona, Spain, April 15-18, 2018, pages 1–6.

Munjal, A., Camp, T., and Navidi, W. C. (2011). Smooth: a simple way to model human mobility. In Proceedings of the 14th ACM international conference on Modeling, analysis and simulation of wireless and mobile systems, pages 351–360. ACM.

Nguyen, H. A. and Giordano, S. (2012). Context information prediction for social-based routing in opportunistic networks. Ad Hoc Networks, 10(8):1557 – 1569.

Schipor, O.-A., Wu, W., Tsai, W.-T., and Vatavu, R.-D. (2017). Software architecture design for spatially-indexed media in smart environments. Advances in Electrical and Computer Engineering, 17(2):17–23.

Silva, T. H., Melo, P. O. S. V. D., Almeida, J. M., and Loureiro, A. A. F. (2014). Large-scale study of city dynamics and urban social behavior using participatory sensing. IEEE Wireless Communications, 21(1):42–51.

Silva, T. H., Viana, A., Benevenuto, F., Villas, L., Salles, J., Loureiro, A., and Quercia, D. (2019). Urban computing leveraging location-based social network data: a survey. ACM Computing Surveys, pages 1–37.

Silveira, L. M., de Almeida, J. M., Marques-Neto, H. T., Sarraute, C., and Ziviani, A. (2016). Mobhet: Predicting human mobility using heterogeneous data sources. Computer Communications, 95:54 – 68. Mobile Traffic Analytics.

Wang, Y., Yuan, N. J., Lian, D., Xu, L., Xie, X., Chen, E., and Rui, Y. (2015). Regularity and conformity: Location prediction using heterogeneous mobility data. In 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’15. ACM.

Yan, X.-Y., Wang, W.-X., Gao, Z.-Y., and Lai, Y.-C. (2017). Universal model of individual and population mobility on diverse spatial scales. Nature Communications, 8(1):1639.