INSTRUCTOR: uma Ferramenta para Análise de Trajetórias Anômalas de Navios por Meio de Algoritmos de Agrupamento
Resumo
Milhares de navios circulam diariamente e a quantidade de incidentes é expressiva, sendo tais ocorrências associadas a trajetórias consideradas anômalas. Os agentes responsáveis pela vigilância marítima precisam ser apoiados por análises visuais da situação para indicação dessas ocorrências, sobretudo de forma antecipada. Neste artigo, apresentamos a ferramenta INSTRUCTOR, que permite a análise visual de trajetórias anômalas de navios usando múltiplos algoritmos de agrupamento (ex. DBSCAN, K-Means, Birch, Spectral Clustering e Ensembles). A INSTRUCTOR pode ser obtida no repositório do GitHub e vem sendo avaliada junto a especialistas da Marinha do Brasil por meio de questionários específicos com roteiros de testes.
Palavras-chave:
Agrupamento de dados, detecção de trajetórias
Referências
De Vries, G. K. D. and Van Someren, M. (2012). Machine learning for vessel trajectories using compression, alignments and domain knowledge. Expert Systems with Applications, 39(18):13426–13439.
Dobrkovic, A., Iacob, M. E., and van Hillegersberg, J. (2015). Using machine learning for unsupervised maritime waypoint discovery from streaming ais data. Proc. of the i-KNOW ’15, pages 1–8.
EMSA (2019). Annual overview of marine casualties and incidents. Technical report.
Ester, M., Kriegel, H. P., Sander, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the KDD’96, page 226–231. AAAI Press.
Kowalska, K. and Peel, L. (2012). Maritime anomaly detection using gaussian process active learning. 2012 15th International Conference on Information Fusion, pages 1164–1171. IEEE.
Ribeiro,C.V.,Paes,A.,and de Oliveira, D.(2023). Ais-based maritime anomaly traffic detection: A review. Expert Systems with Applications, page 120561.
Sidibé, A. and Shu, G. (2017). Study of automatic anomalous behaviour detection techniques for maritime vessels. The journal of Navigation, 70(4):847– 858.
UNCTAD (2019). Handbook of Statistics. United Nations Conference on Trade and Development. Available at [link].
UNCTAD (2022). Handbook of Statistics. United Nations Conference on Trade and Development. Available at [link].
Wang, X., Liu, X., Liu, B., de Souza, E. N., and Matwin, S. (2014). Vessel route anomaly detection with hadoop mapreduce. 2014 IEEE international conference on big data (big data), pages 25–30. IEEE.
Weng, J., Yang, D., Qian, T., and Huang, Z. (2018). Combining zero-inflated negative binomial regression with mlrt techniques: an approach to evaluating shipping accident casualties. Ocean Engineering, 166:135–144.
Zhao, L. and Shi, G. (2019). Maritime anomaly detection using density-based clustering and recurrent neural network. The Journal of Navigation, 72(4):894–916.
Zor, C. and Kittler, J. (2017). Maritime anomaly detection in ferry tracks. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2647–2651. IEEE.
Dobrkovic, A., Iacob, M. E., and van Hillegersberg, J. (2015). Using machine learning for unsupervised maritime waypoint discovery from streaming ais data. Proc. of the i-KNOW ’15, pages 1–8.
EMSA (2019). Annual overview of marine casualties and incidents. Technical report.
Ester, M., Kriegel, H. P., Sander, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the KDD’96, page 226–231. AAAI Press.
Kowalska, K. and Peel, L. (2012). Maritime anomaly detection using gaussian process active learning. 2012 15th International Conference on Information Fusion, pages 1164–1171. IEEE.
Ribeiro,C.V.,Paes,A.,and de Oliveira, D.(2023). Ais-based maritime anomaly traffic detection: A review. Expert Systems with Applications, page 120561.
Sidibé, A. and Shu, G. (2017). Study of automatic anomalous behaviour detection techniques for maritime vessels. The journal of Navigation, 70(4):847– 858.
UNCTAD (2019). Handbook of Statistics. United Nations Conference on Trade and Development. Available at [link].
UNCTAD (2022). Handbook of Statistics. United Nations Conference on Trade and Development. Available at [link].
Wang, X., Liu, X., Liu, B., de Souza, E. N., and Matwin, S. (2014). Vessel route anomaly detection with hadoop mapreduce. 2014 IEEE international conference on big data (big data), pages 25–30. IEEE.
Weng, J., Yang, D., Qian, T., and Huang, Z. (2018). Combining zero-inflated negative binomial regression with mlrt techniques: an approach to evaluating shipping accident casualties. Ocean Engineering, 166:135–144.
Zhao, L. and Shi, G. (2019). Maritime anomaly detection using density-based clustering and recurrent neural network. The Journal of Navigation, 72(4):894–916.
Zor, C. and Kittler, J. (2017). Maritime anomaly detection in ferry tracks. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2647–2651. IEEE.
Publicado
25/09/2023
Como Citar
RIBEIRO, Cláudio V.; PAES, Aline; DE OLIVEIRA, Daniel.
INSTRUCTOR: uma Ferramenta para Análise de Trajetórias Anômalas de Navios por Meio de Algoritmos de Agrupamento. In: DEMONSTRAÇÕES E APLICAÇÕES - SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 38. , 2023, Belo Horizonte/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 84-89.
DOI: https://doi.org/10.5753/sbbd_estendido.2023.233222.
