Modelo de Predição de Escolha de Rotas baseado em Traces de Mobilidade Veicular
Resumo
O estudo da mobilidade veicular e o seu impacto no desenvolvimento das cidades é um tópico importante de pesquisa, contribuindo para o cenário dos Sistemas de Transporte Inteligentes (ITS). Neste trabalho, introduzimos um modelo logit multinomial (MNL) para predizer qual rota um usuário irá tomar dado um conjunto de rotas possíveis entre pontos de origem e destino e outras informações contextuais. Para isso, definimos e aplicamos uma abordagem estatística para entender como os veículos se comportam em um cenário urbano considerando os efeitos do tráfego. O modelo é aplicado em dois rastros reais de mobilidade veicular e os resultados mostram que ele é capaz de capturar as influências dos fatores existentes, obtendo predições superiores em comparação a dois baselines. Os resultados indicam que o modelo pode ser aplicado para o preenchimento de grandes lacunas espaciais, como por exemplo na geração de dados sintéticos porém realísticos de trajetórias para rastros de origem-destino.
Referências
Celes, C., Silva, F. A., Boukerche, A., de Castro Andrade, R. M., and Loureiro, A. A. (2017). Improving vanet simulation with calibrated vehicular mobility traces. Transactions on Mobile Computing, 2017, 16(12):3376–3389.
Chen, Z., Shen, H. T., and Zhou, X. (2011). Discovering popular routes from trajectories. In IEEE 27th Int. Conf. on Data Engineering, pages 900–911.
Cotta, L., de Melo, P. O. V., and Loureiro, A. A. (2017). Understanding the role of mobility in real mobile ad-hoc networks connectivity. In Symp. on Computers and Communications, pages 1098–1103. IEEE.
Domingues, A. C., Silva, F. A., and Loureiro, A. A. (2018). Space and time matter: An analysis about route selection in mobility traces. In Symp. on Computers and Communications, 2018. IEEE.
Harri, J., Filali, F., and Bonnet, C. (2009). Mobility models for vehiIEEE Communications Surveys & cular ad hoc networks: a survey and taxonomy. Tutorials, 11(4).
Hess, A., Hummel, K. A., Gansterer, W. N., and Haring, G. (2016). Data-driven human mobility modeling: a survey and engineering guidance for mobile networking. ACM Computing Surveys, 48(3):38.
Hoteit, S., Chen, G., Viana, A., and Fiore, M. (2016). Filling the gaps: On the completion of sparse call detail records for mobility analysis. In Proceedings of the Eleventh ACM Workshop on Challenged Networks, pages 45–50.
Hoteit, S., Secci, S., Sobolevsky, S., Ratti, C., and Pujolle, G. (2014). Estimating human trajectories and hotspots through mobile phone data. Computer Networks, 64:296–307.
Kotz, D., Henderson, T., Abyzov, and Yeo, (2009). J. Downloaded from I., CRAWDAD dataset dartmouth/campus (v. 2009-09-09). https://crawdad.org/dartmouth/campus/20090909.
Li, M., Ahmed, A., and Smola, A. J. (2015). Inferring movement trajectories from gps snippets. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, pages 325–334. ACM.
Liu, S., Liu, C., Luo, Q., Ni, L. M., and Krishnan, R. (2012a). Calibrating large scale vehicle trajectory data. In Proceedings of the 13th IEEE International Conference on Mobile Data Management, pages 222–231. IEEE.
Liu, Y., Kang, C., Gao, S., Xiao, Y., and Tian, Y. (2012b). Understanding intra-urban trip patterns from taxi trajectory data. Journal of geographical systems, 14(4):463–483.
Lu, X., Cheng, W., Shen, Y., and Zhu, Y. (2019). Ladd: A lengthIn 25th International Conadaptive approach to detecting taxi anomalous detours. ference on Parallel and Distributed Systems, pages 141–144. IEEE.
Mendes-Moreira, J. and Moreira-Matias, L. (2015). On learning from taxi-gps traces. In Proceedings of the 2015th International Conference on ECML PKDD Discovery Challenge-Volume 1526, pages 37–39.
Newson, P. and Krumm, J. (2009). Hidden markov map matching through noise and sparseness. In 17th SIGSPATIAL Int’l Conf. on advances in geographic information systems, pages 336–343. ACM.
Piorkowski, M., Sarafijanovic-Djukic, N., and Grossglauser, M. (2009). Crawdad dataset ep-mobility (v. 2009-02-24). Downloaded from https://crawdad.org/ep/mobility/20090224.
Silva, F. A., Celes, C., Boukerche, A., Ruiz, L. B., and Loureiro, A. A. (2015). Filling the gaps of vehicular mobility traces. In 18th Int’l Conf. on Modeling, Analysis and Simulation of Wireless and Mobile Systems, pages 47–54. ACM.
Su, H., Zheng, K., Huang, J., Wang, H., and Zhou, X. (2015). Calibrating trajectory data for spatio-temporal similarity analysis. Intl’ Journal on Very Large Data Bases, 24(1):93–116.
Teixeira, D. D. C., Viana, A. C., Almeida, J. M., and Alvim, M. S. (2021). The impact of stationarity, regularity, and context on the predictability of individual human mobility. ACM Tran. on Spatial Algorithms and Systems, 7(4):1–24.
Vacca, A. and Meloni, I. (2015). Understanding route switch behavior: An analysis using gps based data. Transportation Res. Procedia, 5:56–65.
Yoon, J., Noble, B. D., Liu, M., and Kim, M. (2006). Building realistic In 4th Int’l Conf. on Mobile Systems, mobility models from coarse-grained traces. Applications and Services, pages 177–190. ACM.
Yuan, H. and Li, G. (2021). A survey of traffic prediction: from spatio-temporal data to intelligent transportation. Data Science and Engineering, 6(1):63–85.
Yuan, J., Zheng, Y., Zhang, C., Xie, W., Xie, X., Sun, G., and Huang, Y. (2010). T-drive: driving directions based on taxi trajectories. In 18th SIGSPATIAL Int’l Conf. on Advances in Geographic Information Systems, pages 99–108. ACM.
Zhu, S. and Levinson, D. (2015). Do people use the shortest path? an empirical test of wardrop’s first principle. PloS one, 10(8):e0134322.
Chen, Z., Shen, H. T., and Zhou, X. (2011). Discovering popular routes from trajectories. In IEEE 27th Int. Conf. on Data Engineering, pages 900–911.
Cotta, L., de Melo, P. O. V., and Loureiro, A. A. (2017). Understanding the role of mobility in real mobile ad-hoc networks connectivity. In Symp. on Computers and Communications, pages 1098–1103. IEEE.
Domingues, A. C., Silva, F. A., and Loureiro, A. A. (2018). Space and time matter: An analysis about route selection in mobility traces. In Symp. on Computers and Communications, 2018. IEEE.
Harri, J., Filali, F., and Bonnet, C. (2009). Mobility models for vehiIEEE Communications Surveys & cular ad hoc networks: a survey and taxonomy. Tutorials, 11(4).
Hess, A., Hummel, K. A., Gansterer, W. N., and Haring, G. (2016). Data-driven human mobility modeling: a survey and engineering guidance for mobile networking. ACM Computing Surveys, 48(3):38.
Hoteit, S., Chen, G., Viana, A., and Fiore, M. (2016). Filling the gaps: On the completion of sparse call detail records for mobility analysis. In Proceedings of the Eleventh ACM Workshop on Challenged Networks, pages 45–50.
Hoteit, S., Secci, S., Sobolevsky, S., Ratti, C., and Pujolle, G. (2014). Estimating human trajectories and hotspots through mobile phone data. Computer Networks, 64:296–307.
Kotz, D., Henderson, T., Abyzov, and Yeo, (2009). J. Downloaded from I., CRAWDAD dataset dartmouth/campus (v. 2009-09-09). https://crawdad.org/dartmouth/campus/20090909.
Li, M., Ahmed, A., and Smola, A. J. (2015). Inferring movement trajectories from gps snippets. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, pages 325–334. ACM.
Liu, S., Liu, C., Luo, Q., Ni, L. M., and Krishnan, R. (2012a). Calibrating large scale vehicle trajectory data. In Proceedings of the 13th IEEE International Conference on Mobile Data Management, pages 222–231. IEEE.
Liu, Y., Kang, C., Gao, S., Xiao, Y., and Tian, Y. (2012b). Understanding intra-urban trip patterns from taxi trajectory data. Journal of geographical systems, 14(4):463–483.
Lu, X., Cheng, W., Shen, Y., and Zhu, Y. (2019). Ladd: A lengthIn 25th International Conadaptive approach to detecting taxi anomalous detours. ference on Parallel and Distributed Systems, pages 141–144. IEEE.
Mendes-Moreira, J. and Moreira-Matias, L. (2015). On learning from taxi-gps traces. In Proceedings of the 2015th International Conference on ECML PKDD Discovery Challenge-Volume 1526, pages 37–39.
Newson, P. and Krumm, J. (2009). Hidden markov map matching through noise and sparseness. In 17th SIGSPATIAL Int’l Conf. on advances in geographic information systems, pages 336–343. ACM.
Piorkowski, M., Sarafijanovic-Djukic, N., and Grossglauser, M. (2009). Crawdad dataset ep-mobility (v. 2009-02-24). Downloaded from https://crawdad.org/ep/mobility/20090224.
Silva, F. A., Celes, C., Boukerche, A., Ruiz, L. B., and Loureiro, A. A. (2015). Filling the gaps of vehicular mobility traces. In 18th Int’l Conf. on Modeling, Analysis and Simulation of Wireless and Mobile Systems, pages 47–54. ACM.
Su, H., Zheng, K., Huang, J., Wang, H., and Zhou, X. (2015). Calibrating trajectory data for spatio-temporal similarity analysis. Intl’ Journal on Very Large Data Bases, 24(1):93–116.
Teixeira, D. D. C., Viana, A. C., Almeida, J. M., and Alvim, M. S. (2021). The impact of stationarity, regularity, and context on the predictability of individual human mobility. ACM Tran. on Spatial Algorithms and Systems, 7(4):1–24.
Vacca, A. and Meloni, I. (2015). Understanding route switch behavior: An analysis using gps based data. Transportation Res. Procedia, 5:56–65.
Yoon, J., Noble, B. D., Liu, M., and Kim, M. (2006). Building realistic In 4th Int’l Conf. on Mobile Systems, mobility models from coarse-grained traces. Applications and Services, pages 177–190. ACM.
Yuan, H. and Li, G. (2021). A survey of traffic prediction: from spatio-temporal data to intelligent transportation. Data Science and Engineering, 6(1):63–85.
Yuan, J., Zheng, Y., Zhang, C., Xie, W., Xie, X., Sun, G., and Huang, Y. (2010). T-drive: driving directions based on taxi trajectories. In 18th SIGSPATIAL Int’l Conf. on Advances in Geographic Information Systems, pages 99–108. ACM.
Zhu, S. and Levinson, D. (2015). Do people use the shortest path? an empirical test of wardrop’s first principle. PloS one, 10(8):e0134322.
Publicado
16/08/2021
Como Citar
DOMINGUES, Augusto C. S. A.; PINTO, Letícia; SILVA, Fabrício A.; LOSCHI, Rosângela H.; LOUREIRO, Antonio A. F..
Modelo de Predição de Escolha de Rotas baseado em Traces de Mobilidade Veicular. In: WORKSHOP DE COMPUTAÇÃO URBANA (COURB), 5. , 2021, Uberlândia.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 126-139.
ISSN 2595-2706.
DOI: https://doi.org/10.5753/courb.2021.17109.
