Uma Estratégia Híbrida para o Problema de Classificação Multirrótulo
Resumo
A aprendizagem de classificadores multirrótulo se originou na categorização de textos, onde cada documento podia pertencer a mais de uma classe simultaneamente e tem atraído muita atenção como consequência tanto do desafio de pesquisa que representa quanto da relevância dos seus cenários de aplicação. Neste artigo, propomos uma nova abordagem híbrida, Multi Label k-Nearest Michigan Particle Swarm Optimization (ML-KMPSO), que é baseada em duas estratégias. A primeira é a divisão do problema multirrótulo em diversos problemas binários, para tal foi utilizado o Michigan Particle Swarm Optimization (MPSO) para resolve-los, mais esta estratégia não leva em consideração as correlações existentes entre as classes. Já a segunda estratégia tem como objetivo considerar as correlações existentes entre as classes utilizando o Multi Label K-Nearest Neighbor (ML-KNN). Avaliamos o desempenho do ML-KMPSO utilizando duas bases de dados reais e os resultados mostram que a nossa proposta se iguala ou supera algoritmos estado-da-arte de classificação multirrótulo.Referências
Boutell, M. R., Luo, J., Shen, X., and Brown, C. M. (2004). Learning multi-label scene classification. Pattern Recognition, 37(9):1757–1771.
Cervantes, A., Galván, I. M., and Isasi, P. (2009a). Ampso: a new particle swarm method for nearest neighborhood classification. Trans. Sys. Man Cyber. Part B, 39:1082–1091.
Cervantes, A., Galván, I. M., and Viñuela, P. I. (2009b). Michigan particle swarm optimization for prototype reduction in classification problems. New Generation Comput., 27(3):239–257.
de Carvalho, A. and Freitas, A. (2009). A tutorial on multi-label classification techniques, volume Foundations of Computational Intelligence Vol. 5 of Studies in Computational Intelligence 205, pages 177–195. Springer.
Eberhart, R. and Kennedy, J. (1995). A new optimizer using particle swarm theory. pages 39–43.
Elisseeff, A. and Weston, J. (2001). A kernel method for multi-labelled classification. In In Advances in Neural Information Processing Systems 14, pages 681–687. MIT Press.
Elisseeff, A. and Weston, J. (2005). A kernel method for multi-labelled classification. In Annual ACM Conference on Research and Development in Information Retrieval, pages 274–281.
Esmin, A. A. A. (2007). Generating fuzzy rules from examples using the particle swarm optimization algorithm. In HIS, pages 340–343.
Kennedy, J. and Eberhart, R. (1995). Particle swarm optimization. In Neural Networks, 1995. Proceedings., IEEE International Conference on, volume 4, pages 1942–1948 vol.4.
Li, T., Zhang, C., and Zhu, S. (2006). Empirical studies on multi-label classification. In ICTAI ’06: Proceedings of the 18th IEEE International Conference on Tools with Artificial Intelligence, pages 86–92, Washington, DC, USA. IEEE Computer Society.
Quinlan, J. R. (1993). C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.
Schapire, R. E. and Singer, Y. (2000). BoosTexter: A Boosting-based System for Text Categorization. Machine Learning, 39(2/3):135–168.
Sousa, T., Silva, A., and Neves, A. (2004). Particle swarm based data mining algorithms for classification tasks. Parallel Comput., 30(5-6):767–783.
Trohidis, K., Tsoumakas, G., Kalliris, G., and Vlahavas, I. (2008). Multilabel classification of music into emotions. In Proc. 9th International Conference on Music Information Retrieval (ISMIR 2008), Philadelphia, PA, USA, 2008.
Wang, Z., Sun, X., and Zhang, D. (2006). Classification rule mining based on particle swarm optimization. In RSKT, pages 436–441.
Wang, Z., Sun, X., and Zhang, D. (2007). A pso-based classification rule mining algorithm. In Huang, D.-S., Heutte, L., and Loog, M., editors, Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence, volume 4682 of Lecture Notes in Computer Science, pages 377–384. Springer Berlin / Heidelberg.
Zhang, M.-L. and Zhou, Z.-H. (2005). A k-nearest neighbor based algorithm for multi-label classification. In GrC, pages 718–721.
Zhang, M.-L. and Zhou, Z.-H. (2006). Multilabel neural networks with applications to functional genomics and text categorization. IEEE Transactions on Knowledge and Data Engineering, 18:1338–1351.
Zhang, M.-L. and Zhou, Z.-H. (2007). ML-KNN: A lazy learning approach to multi-label learning. Pattern Recognition, 40(7):2038–2048.
Cervantes, A., Galván, I. M., and Isasi, P. (2009a). Ampso: a new particle swarm method for nearest neighborhood classification. Trans. Sys. Man Cyber. Part B, 39:1082–1091.
Cervantes, A., Galván, I. M., and Viñuela, P. I. (2009b). Michigan particle swarm optimization for prototype reduction in classification problems. New Generation Comput., 27(3):239–257.
de Carvalho, A. and Freitas, A. (2009). A tutorial on multi-label classification techniques, volume Foundations of Computational Intelligence Vol. 5 of Studies in Computational Intelligence 205, pages 177–195. Springer.
Eberhart, R. and Kennedy, J. (1995). A new optimizer using particle swarm theory. pages 39–43.
Elisseeff, A. and Weston, J. (2001). A kernel method for multi-labelled classification. In In Advances in Neural Information Processing Systems 14, pages 681–687. MIT Press.
Elisseeff, A. and Weston, J. (2005). A kernel method for multi-labelled classification. In Annual ACM Conference on Research and Development in Information Retrieval, pages 274–281.
Esmin, A. A. A. (2007). Generating fuzzy rules from examples using the particle swarm optimization algorithm. In HIS, pages 340–343.
Kennedy, J. and Eberhart, R. (1995). Particle swarm optimization. In Neural Networks, 1995. Proceedings., IEEE International Conference on, volume 4, pages 1942–1948 vol.4.
Li, T., Zhang, C., and Zhu, S. (2006). Empirical studies on multi-label classification. In ICTAI ’06: Proceedings of the 18th IEEE International Conference on Tools with Artificial Intelligence, pages 86–92, Washington, DC, USA. IEEE Computer Society.
Quinlan, J. R. (1993). C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.
Schapire, R. E. and Singer, Y. (2000). BoosTexter: A Boosting-based System for Text Categorization. Machine Learning, 39(2/3):135–168.
Sousa, T., Silva, A., and Neves, A. (2004). Particle swarm based data mining algorithms for classification tasks. Parallel Comput., 30(5-6):767–783.
Trohidis, K., Tsoumakas, G., Kalliris, G., and Vlahavas, I. (2008). Multilabel classification of music into emotions. In Proc. 9th International Conference on Music Information Retrieval (ISMIR 2008), Philadelphia, PA, USA, 2008.
Wang, Z., Sun, X., and Zhang, D. (2006). Classification rule mining based on particle swarm optimization. In RSKT, pages 436–441.
Wang, Z., Sun, X., and Zhang, D. (2007). A pso-based classification rule mining algorithm. In Huang, D.-S., Heutte, L., and Loog, M., editors, Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence, volume 4682 of Lecture Notes in Computer Science, pages 377–384. Springer Berlin / Heidelberg.
Zhang, M.-L. and Zhou, Z.-H. (2005). A k-nearest neighbor based algorithm for multi-label classification. In GrC, pages 718–721.
Zhang, M.-L. and Zhou, Z.-H. (2006). Multilabel neural networks with applications to functional genomics and text categorization. IEEE Transactions on Knowledge and Data Engineering, 18:1338–1351.
Zhang, M.-L. and Zhou, Z.-H. (2007). ML-KNN: A lazy learning approach to multi-label learning. Pattern Recognition, 40(7):2038–2048.
Publicado
19/07/2011
Como Citar
COELHO, Tiago Amador; ESMIN, Ahmed Ali Abdalla; MEIRA JÚNIOR, Wagner.
Uma Estratégia Híbrida para o Problema de Classificação Multirrótulo. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 8. , 2011, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2011
.
p. 914-925.
ISSN 2763-9061.
