Um modelo para seleção automática de algoritmos de extração de eventos de trânsito para aplicações ITS
Resumo
Eventos de trânsito podem ser úteis para uma variedade de aplicações de sistemas de transporte inteligente (Intelligent Transportation Systems (ITS)). Este trabalho apresenta um modelo capaz de correlacionar características de múltiplas fontes de dados com demandas de aplicações ITS interessadas em consumir eventos de trânsito para estabelecer a melhor estratégia para extraí-los. Uma vez utilizado, o modelo leva a uma lista de eventos, cada um deles reportando o que aconteceu, além de onde e quando. Uma instância do modelo proposto usando duas redes sociais como fontes de dados e quatro algoritmos de aprendizado de máquina foi implementada como estudo de caso. Os resultados mostraram que foi possível detectar uma grande parte dos eventos esperados, todos com suas informações completas sobre o que, onde e quando.
Palavras-chave:
Eventos, Sistemas de Transporte Inteligente, Aprendizado de Máquina
Referências
Albuquerque, F. C., Casanova, M. A., Lopes, H., Redlich, L. R., de Macedo, J. A. F.,Lemos, M., de Carvalho, M. T. M., and Renso, C. (2016). A methodology for traffic-related twitter messages interpretation.Computers in Industry, 78:57–69.
Allan, J., Papka, R., and Lavrenko, V. (1998). On-line new event detection and tracking.InProceedings of the 21st annual international ACM SIGIR conference on Researchand development in information retrieval, pages 37–45. ACM.
Anantharam, P., Barnaghi, P., Thirunarayan, K., and Sheth, A. (2015). Extracting citytraffic events from social streams.ACM Transactions on Intelligent Systems and Tech-nology (TIST), 6(4):43
Brants, T., Chen, F., and Farahat, A. (2003). A system for new event detection. In Proceedings of the 26th annual international ACM SIGIR conference on Research anddevelopment in informaion retrieval, pages 330–337. ACM
Finkel, J. R. and Manning, C. D. (2009). Nested named entity recognition. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing:Volume 1-Volume 1, pages 141–150. Association for Computational Linguistics.
Galton, A. and Augusto, J. C. (2002). Two approaches to event definition. In International Conference on Database and Expert Systems Applications, pages 547–556. Springer
Kokkinogenis, Z., Filguieras, J., Carvalho, S., Sarmento, L., and Rossetti, R. (2015). Mobility network evaluation in the user perspective: Real-time sensing of traffic informa-tion in twitter messages.Advances in Artificial Transportation Systems and Simulation,pages 219–234
Kumaran, G., Allan, J., and McCallum, A. (2004). Classification models for new eventdetection. In International conference on information and knowledge management(CIKM2004).
Petalas, Y. G., Ammari, A., Georgakis, P., and Nwagboso, C. (2016). A big data architecture for traffic forecasting using multi-source information. InInternational Workshopof Algorithmic Aspects of Cloud Computing, pages 65–83. Springer.
Ratinov, L. and Roth, D. (2009). Design challenges and misconceptions in named entityrecognition. In Proceedings of the thirteenth conference on computational naturallanguage learning, pages 147–155. Association for Computational Linguistics.
Ribeiro Jr, S. S., Davis Jr, C. A., Oliveira, D. R. R., Meira Jr, W., Gonçalves, T. S., andPappa, G. L. (2012). Traffic observatory: a system to detect and locate traffic eventsand conditions using twitter. InProceedings of the 5th ACM SIGSPATIAL InternationalWorkshop on Location-Based Social Networks, pages 5–11. ACM
Sakaki, T., Matsuo, Y., Yanagihara, T., Chandrasiri, N. P., and Nawa, K. (2012). Real-time event extraction for driving information from social sensors. InCyber Technologyin Automation, Control, and Intelligent Systems (CYBER), 2012 IEEE International Conference on, pages 221–226. IEEE
Tejaswin, P., Kumar, R., and Gupta, S. (2015). Tweeting traffic: Analyzing twitter forgenerating real-time city traffic insights and predictions. InProceedings of the 2ndIKDD Conference on Data Sciences, page 9. ACM
Wang, D., Al-Rubaie, A., Davies, J., and Clarke, S. S. (2014). Real time road traffic mo-nitoring alert based on incremental learning from tweets. InEvolving and AutonomousLearning Systems (EALS), 2014 IEEE Symposium on, pages 50–57. IEEE
Zhang, Y., Jin, R., and Zhou, Z.-H. (2010). Understanding bag-of-words model: a statistical framework.International Journal of Machine Learning and Cybernetics, 1(1-4):43–52
Allan, J., Papka, R., and Lavrenko, V. (1998). On-line new event detection and tracking.InProceedings of the 21st annual international ACM SIGIR conference on Researchand development in information retrieval, pages 37–45. ACM.
Anantharam, P., Barnaghi, P., Thirunarayan, K., and Sheth, A. (2015). Extracting citytraffic events from social streams.ACM Transactions on Intelligent Systems and Tech-nology (TIST), 6(4):43
Brants, T., Chen, F., and Farahat, A. (2003). A system for new event detection. In Proceedings of the 26th annual international ACM SIGIR conference on Research anddevelopment in informaion retrieval, pages 330–337. ACM
Finkel, J. R. and Manning, C. D. (2009). Nested named entity recognition. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing:Volume 1-Volume 1, pages 141–150. Association for Computational Linguistics.
Galton, A. and Augusto, J. C. (2002). Two approaches to event definition. In International Conference on Database and Expert Systems Applications, pages 547–556. Springer
Kokkinogenis, Z., Filguieras, J., Carvalho, S., Sarmento, L., and Rossetti, R. (2015). Mobility network evaluation in the user perspective: Real-time sensing of traffic informa-tion in twitter messages.Advances in Artificial Transportation Systems and Simulation,pages 219–234
Kumaran, G., Allan, J., and McCallum, A. (2004). Classification models for new eventdetection. In International conference on information and knowledge management(CIKM2004).
Petalas, Y. G., Ammari, A., Georgakis, P., and Nwagboso, C. (2016). A big data architecture for traffic forecasting using multi-source information. InInternational Workshopof Algorithmic Aspects of Cloud Computing, pages 65–83. Springer.
Ratinov, L. and Roth, D. (2009). Design challenges and misconceptions in named entityrecognition. In Proceedings of the thirteenth conference on computational naturallanguage learning, pages 147–155. Association for Computational Linguistics.
Ribeiro Jr, S. S., Davis Jr, C. A., Oliveira, D. R. R., Meira Jr, W., Gonçalves, T. S., andPappa, G. L. (2012). Traffic observatory: a system to detect and locate traffic eventsand conditions using twitter. InProceedings of the 5th ACM SIGSPATIAL InternationalWorkshop on Location-Based Social Networks, pages 5–11. ACM
Sakaki, T., Matsuo, Y., Yanagihara, T., Chandrasiri, N. P., and Nawa, K. (2012). Real-time event extraction for driving information from social sensors. InCyber Technologyin Automation, Control, and Intelligent Systems (CYBER), 2012 IEEE International Conference on, pages 221–226. IEEE
Tejaswin, P., Kumar, R., and Gupta, S. (2015). Tweeting traffic: Analyzing twitter forgenerating real-time city traffic insights and predictions. InProceedings of the 2ndIKDD Conference on Data Sciences, page 9. ACM
Wang, D., Al-Rubaie, A., Davies, J., and Clarke, S. S. (2014). Real time road traffic mo-nitoring alert based on incremental learning from tweets. InEvolving and AutonomousLearning Systems (EALS), 2014 IEEE Symposium on, pages 50–57. IEEE
Zhang, Y., Jin, R., and Zhou, Z.-H. (2010). Understanding bag-of-words model: a statistical framework.International Journal of Machine Learning and Cybernetics, 1(1-4):43–52
Publicado
18/07/2021
Como Citar
PEREIRA, Alexandra S.; SILVA, Thais R. M. B.; SILVA, Fabrício A.; CORREIA, Luiz H. A.; LOUREIRO, Antonio A. F..
Um modelo para seleção automática de algoritmos de extração de eventos de trânsito para aplicações ITS. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO UBÍQUA E PERVASIVA (SBCUP), 13. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 51-60.
ISSN 2595-6183.
DOI: https://doi.org/10.5753/sbcup.2021.16003.
