Busca avançada
Ano de início
Entree
(Referência obtida automaticamente do Web of Science, por meio da informação sobre o financiamento pela FAPESP e o número do processo correspondente, incluída na publicação pelos autores.)

Inducing Hierarchical Multi-label Classification rules with Genetic Algorithms

Texto completo
Autor(es):
Cerri, Ricardo [1] ; Basgalupp, Marcio P. [2] ; Barros, Rodrigo C. [3] ; de Carvalho, Andre C. P. L. F. [4]
Número total de Autores: 4
Afiliação do(s) autor(es):
[1] Univ Fed Sao Carlos, Dept Comp Sci, Sao Carlos, SP - Brazil
[2] Univ Fed Sao Paulo, Inst Ciencia & Tecnol, Sao Paulo, SP - Brazil
[3] Pontificia Univ Catolica Rio Grande do Sul, Sch Technol, Porto Alegre, RS - Brazil
[4] Univ Sao Paulo, Inst Ciencias Matemat & Comp, Sao Paulo - Brazil
Número total de Afiliações: 4
Tipo de documento: Artigo Científico
Fonte: APPLIED SOFT COMPUTING; v. 77, p. 584-604, APR 2019.
Citações Web of Science: 1
Resumo

Hierarchical Multi-Label Classification is a challenging classification task where the classes are hierarchically structured, with superclass and subclass relationships. It is a very common task, for instance, in Protein Function Prediction, where a protein can simultaneously perform multiple functions. In these tasks it is very difficult to achieve a high predictive performance, since hundreds or even thousands of classes with imbalanced data distributions have to be considered. In addition, the models should ideally be easily interpretable to allow the validation of the knowledge extracted from the data. This work proposes and investigates the use of Genetic Algorithms to induce rules that are both hierarchical and multi-label. Several experiments with different fitness functions and genetic operators are preformed to obtain different Hierarchical Multi-Label Classification rules. The different proposed configurations of Genetic Algorithms are evaluated together with state-of-the-art methods for HMC rule induction based on Ant Colony Optimization and Predictive Clustering Trees, using many datasets related to the Protein Function Prediction task. The experimental results show that it is possible to recommend the best configuration in terms of predictive performance and model interpretability. (C) 2019 Elsevier B.V. All rights reserved. (AU)

Processo FAPESP: 15/14300-1 - Classificação hierárquica de elementos transponíveis utilizando aprendizado de máquina
Beneficiário:Ricardo Cerri
Linha de fomento: Auxílio à Pesquisa - Regular
Processo FAPESP: 16/50457-5 - Multi-objective evolutionary methods for hierarchical and multi-label classification
Beneficiário:Ricardo Cerri
Linha de fomento: Auxílio à Pesquisa - Regular