Hervás-Martínez C. , MARTÍNEZ ESTUDILLO, FRANCISCO JOSÉ
No
Pattern Recogn.
Article
Científica
2.019
1.275
01/01/2007
000241837300005
2-s2.0-33749267856
We propose a logistic regression method based on the hybridation of a linear model and product-unit neural network models for binary classification. In a first step we use an evolutionary algorithm to determine the basic structure of the product-unit model and afterwards we apply logistic regression in the new space of the derived features. This hybrid model has been applied to seven benchmark data sets and a new microbiological problem. The hybrid model outperforms the linear part and the nonlinear part obtaining a good compromise between them and they perform well compared to several other learning classification techniques. We obtain a binary classifier with very promising results in terms of classification accuracy and the complexity of the classifier. © 2006 Pattern Recognition Society.
Classification (of information); Computational complexity; Evolutionary algorithms; Mathematical models; Neural networks; Problem solving; Benchmark data sets; Logistic regression; Product-unit neural network; Regression analysis