Avaliação do Algoritmo de Stacking em Dados Biomédicos
Resumo
O stacking é uma técnica de combinação de classificadores bem estudada, mas ainda com muitos aspectos a explorar, e.g., não existem recomendações sobre quais e quantos algoritmos devem ser utilizados no nível-0 nem qual algoritmo deve compor o meta-classificador do nível-1. A literatura indica que o meta-algoritmo do nível-1 deve ser simples, sendo Naive Bayes geralmente utilizado nos estudos. Neste estudo analisou-se stacking em conjuntos de dados biomédicos, utilizando três paradigmas de aprendizado de máquina para o meta-classificador. Os experimentos mostram que meta-algoritmos simples não apresentam bons resultados, indicando que devem ter certo grau de complexidade para obterem bom desempenho.
Referências
Aha, D. W., Kibler, D. & Albert, M. K. (1991) “Instance based learning algorithms” In Machine Learning, p. 37–66.
Benjamini, Y. & Hochberg, Y. (1995) “Controlling the false discovery rate: a practical and powerful approach to multiple testing”, In Journal of the Royal Statistical Society Series B, v. 57, p. 289–300.
Bradley, A. P. (1997) “The use of the area under the ROC curve in the evaluation of machine learning algorithms”. Pattern Recognition 30(7), 1145–1159.
Chickering, D. M., Heckerman, D. & Meek, C. (2005) “Learning of Bayesian Networks is NP – Hard” In Journal of Machine Learning Research, 5, p 1287–1330.
Cohen, W. W. (1995) “Fast effective rule induction” In Proceedings of Twelfth International Conference on Machine Learning, p. 115–123.
Dzeroski, S. & Zenko B. (2002) “Is combining Classifiers Better than Selecting the Best One?” In Proceedings of the 19th International Conference on Machine Learning, Morgan Kaufmann Publishers, San Francisco.
Frank, A. & Asuncion, A. (2010) “UCI Machine Learning Repository”, [link], School of Information and Computer Science, University of California at Irvine, Irvine CA.
Friedman, M. (1940) “A comparison of alternative tests of significance for the problem of m rankings”. The Annals of Mathematical Statistics 11(1), 86–92.
Haykin, S. (1998) Neural networks: a comprehensive foundation, 2nd edition, Pearson Education, London.
Iba, W. & Langley, P. (1992) “Induction of One – Level Decision Trees” In Proceedings of the Ninth International Conference on Machine Learning.
Nemenyi, P. B. (1963) Distribution-free multiple comparisons, PhD. Thesis, Princeton University.
Pereira, M. & Schmitz, A. (2010) "Inteligência Artificial e Geotecnologias Emergentes Aplicadas em Estudos Ecoepidemiológicos de Malária no Município de Bragança-Pará, Brasil, no Período de 2006 a 2008", In Proceedings do X Workshop de Informática Médica, Congresso da Sociedade Brasileira de Computação, p. 1630–1640, Belo Horizonte.
Pollettini, J. T., Tinos, R., Panico, S., Daneluzzi, J. C. & Macedo, A. A. (2009) "Vigilância em atenção básica à saúde a partir do uso de relevance feedback para classificação de pacientes em diferentes níveis de cuidado em saúde", In Proceedings do IX Workshop de Informática Médica, Congresso da Sociedade Brasileira de Computação, p. 1945–1954, Bento Gonçalves.
Quinlan, J. R. (1993) C4.5: programs for machine learning, Morgan Kaufmann, San Francisco.
Rish, I. (2001) “An empirical study of the naive Bayes classifier”, In IJCAI Workshop on Empirical Methods in Artificial Intelligence, p. 41–46.
Seewald, A. K. (2002) “How to make Stacking Better and Faster While Also Taking Care of an Unknown Weakness”, In Proceedings of the 19th International Conference on Machine Learning, p. 554–561, Morgan Kaufmann Publishers, Sydney.
Seewald, A. K. (2002) “Exploring the Parameter State Space of Stacking”, In Proceedings of the 2002 IEEE International Conference of Data Mining (ICDM'02), p. 685–688.
Tanwani, A. K., Afridi, J. Shafiq, M. Z. & Farroq, M. (2009) “Guidelines to Select Machine Learning Scheme for Classification of Biomedical Datasets”, C.Pizzuti, M.D. Ritchie, & M. Giacobini, LNCS 5483, Springer-Verlag Berlin Heidelberg 2009, p. 128–139.
Vapnik, V. N. (1998) Statistical learning theory, Wiley Interscience, USA.
Witten, I. H. & Frank, E. (2005) Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, 2. ed.: Morgan Kaufmann.
Wolpert, D. H. (1992) Stacked Generalization. In Neural Networks, p. 241–260.
Benjamini, Y. & Hochberg, Y. (1995) “Controlling the false discovery rate: a practical and powerful approach to multiple testing”, In Journal of the Royal Statistical Society Series B, v. 57, p. 289–300.
Bradley, A. P. (1997) “The use of the area under the ROC curve in the evaluation of machine learning algorithms”. Pattern Recognition 30(7), 1145–1159.
Chickering, D. M., Heckerman, D. & Meek, C. (2005) “Learning of Bayesian Networks is NP – Hard” In Journal of Machine Learning Research, 5, p 1287–1330.
Cohen, W. W. (1995) “Fast effective rule induction” In Proceedings of Twelfth International Conference on Machine Learning, p. 115–123.
Dzeroski, S. & Zenko B. (2002) “Is combining Classifiers Better than Selecting the Best One?” In Proceedings of the 19th International Conference on Machine Learning, Morgan Kaufmann Publishers, San Francisco.
Frank, A. & Asuncion, A. (2010) “UCI Machine Learning Repository”, [link], School of Information and Computer Science, University of California at Irvine, Irvine CA.
Friedman, M. (1940) “A comparison of alternative tests of significance for the problem of m rankings”. The Annals of Mathematical Statistics 11(1), 86–92.
Haykin, S. (1998) Neural networks: a comprehensive foundation, 2nd edition, Pearson Education, London.
Iba, W. & Langley, P. (1992) “Induction of One – Level Decision Trees” In Proceedings of the Ninth International Conference on Machine Learning.
Nemenyi, P. B. (1963) Distribution-free multiple comparisons, PhD. Thesis, Princeton University.
Pereira, M. & Schmitz, A. (2010) "Inteligência Artificial e Geotecnologias Emergentes Aplicadas em Estudos Ecoepidemiológicos de Malária no Município de Bragança-Pará, Brasil, no Período de 2006 a 2008", In Proceedings do X Workshop de Informática Médica, Congresso da Sociedade Brasileira de Computação, p. 1630–1640, Belo Horizonte.
Pollettini, J. T., Tinos, R., Panico, S., Daneluzzi, J. C. & Macedo, A. A. (2009) "Vigilância em atenção básica à saúde a partir do uso de relevance feedback para classificação de pacientes em diferentes níveis de cuidado em saúde", In Proceedings do IX Workshop de Informática Médica, Congresso da Sociedade Brasileira de Computação, p. 1945–1954, Bento Gonçalves.
Quinlan, J. R. (1993) C4.5: programs for machine learning, Morgan Kaufmann, San Francisco.
Rish, I. (2001) “An empirical study of the naive Bayes classifier”, In IJCAI Workshop on Empirical Methods in Artificial Intelligence, p. 41–46.
Seewald, A. K. (2002) “How to make Stacking Better and Faster While Also Taking Care of an Unknown Weakness”, In Proceedings of the 19th International Conference on Machine Learning, p. 554–561, Morgan Kaufmann Publishers, Sydney.
Seewald, A. K. (2002) “Exploring the Parameter State Space of Stacking”, In Proceedings of the 2002 IEEE International Conference of Data Mining (ICDM'02), p. 685–688.
Tanwani, A. K., Afridi, J. Shafiq, M. Z. & Farroq, M. (2009) “Guidelines to Select Machine Learning Scheme for Classification of Biomedical Datasets”, C.Pizzuti, M.D. Ritchie, & M. Giacobini, LNCS 5483, Springer-Verlag Berlin Heidelberg 2009, p. 128–139.
Vapnik, V. N. (1998) Statistical learning theory, Wiley Interscience, USA.
Witten, I. H. & Frank, E. (2005) Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, 2. ed.: Morgan Kaufmann.
Wolpert, D. H. (1992) Stacked Generalization. In Neural Networks, p. 241–260.
Publicado
19/07/2011
Como Citar
CAFFÉ, Maria Izabela R.; PEREZ, Pedro Santoro; BARANAUSKAS, José Augusto.
Avaliação do Algoritmo de Stacking em Dados Biomédicos. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 11. , 2011, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2011
.
p. 1830-1839.
ISSN 2763-8952.
