Genetic Programming for Feature Selection and Construction to High-Dimensional Data

Created by W.Langdon from gp-bibliography.bib Revision:1.8360

@InProceedings{Ma:2024:MLISE,

• author = "Jianbin Ma and Man Zhu",
• title = "Genetic Programming for Feature Selection and Construction to High-Dimensional Data",
• booktitle = "2024 4th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)",
• year = "2024",
• pages = "196--200",
• month = jun,
• keywords = "genetic algorithms, genetic programming, Feature extraction, Decision trees, Intelligent systems, Feature Construction, Feature Selection, High-dimensional, Classification",
• DOI = "doi:10.1109/MLISE62164.2024.10674630",
• abstract = "Classification on high-dimensional data is a challenging task due to a large number of redundant and irrelevant features. Feature construction using Genetic Programming (GP) is an effective feature processing approach for classification, however, in high-dimensional applications, too many redundant and irrelevant features may reduce GP's search ability and affect the classification performance of feature construction. In this paper, two feature selection and construction approaches to high-dimensional data are proposed. The first is a two-stage feature selection and construction approach named LfsFc, which first uses linear forword feature selection method (Lfs) to reduce the search space of features, and then uses a GP-based multiple feature construction approach (Fc) to construct multiple features. The second is a multi-objective GP-based feature selection and construction approach named MoFc which optimises information gain ratio and the number of selected features, and archives elite individuals as constructed features. Experiments on ten high-dimensional datasets show that LfsFc and MoFc can improve the classification performance compared with Fc and original features in four decision tree classifiers.",
• notes = "Also known as \cite{10674630}",

}

Genetic Programming entries for Jianbin Ma Man Zhu

Citations