An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees

This study addresses the challenge of generating accurate and compact oblique decision trees using self-adaptive differential evolution algorithms. Although traditional decision tree induction methods create explainable models, they often fail to achieve optimal classification accuracy. To overcome...

Full description

Saved in:
Bibliographic Details
Main Authors: Rafael Rivera-López, Efrén Mezura-Montes, Juana Canul-Reich, Marco-Antonio Cruz-Chávez
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Mathematical and Computational Applications
Subjects:
Online Access:https://www.mdpi.com/2297-8747/29/6/103
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846103828894580736
author Rafael Rivera-López
Efrén Mezura-Montes
Juana Canul-Reich
Marco-Antonio Cruz-Chávez
author_facet Rafael Rivera-López
Efrén Mezura-Montes
Juana Canul-Reich
Marco-Antonio Cruz-Chávez
author_sort Rafael Rivera-López
collection DOAJ
description This study addresses the challenge of generating accurate and compact oblique decision trees using self-adaptive differential evolution algorithms. Although traditional decision tree induction methods create explainable models, they often fail to achieve optimal classification accuracy. To overcome these limitations, other strategies, such as those based on evolutionary computation, have been proposed in the literature. In particular, we evaluate the use of self-adaptive differential evolution variants to evolve a population of oblique decision trees encoded as real-valued vectors. Our proposal includes (1) an alternative initialization strategy that reduces redundant nodes and (2) a fitness function that penalizes excessive leaf nodes, promoting smaller and more accurate decision trees. We perform a comparative performance analysis of these differential evolution variants, showing that while they exhibit similar statistical behavior, the Single-Objective real-parameter optimization (jSO) method produces the most accurate oblique decision trees and is second best in compactness. The findings highlight the potential of self-adaptive differential evolution algorithms to improve the effectiveness of oblique decision trees in machine learning applications.
format Article
id doaj-art-f29650f238914cba8b661a04cf5e9ecc
institution Kabale University
issn 1300-686X
2297-8747
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Mathematical and Computational Applications
spelling doaj-art-f29650f238914cba8b661a04cf5e9ecc2024-12-27T14:38:25ZengMDPI AGMathematical and Computational Applications1300-686X2297-87472024-11-0129610310.3390/mca29060103An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision TreesRafael Rivera-López0Efrén Mezura-Montes1Juana Canul-Reich2Marco-Antonio Cruz-Chávez3Departamento de Sistemas y Computación, Tecnológico Nacional de México, Instituto Tecnológico de Veracruz, Veracruz 91897, MexicoInstituto de Investigaciones en Inteligencia Artificial, Universidad Veracruzana, Xalapa 91097, MexicoDivisión Académica de Ciencias y Tecnologías de la Información, Universidad Juárez Autónoma de Tabasco, Cunduacán 86690, MexicoCentro de Investigación en Ingeniería y Ciencias Aplicadas, Universidad Autónoma del Estado de Morelos, Cuernavaca 62209, MexicoThis study addresses the challenge of generating accurate and compact oblique decision trees using self-adaptive differential evolution algorithms. Although traditional decision tree induction methods create explainable models, they often fail to achieve optimal classification accuracy. To overcome these limitations, other strategies, such as those based on evolutionary computation, have been proposed in the literature. In particular, we evaluate the use of self-adaptive differential evolution variants to evolve a population of oblique decision trees encoded as real-valued vectors. Our proposal includes (1) an alternative initialization strategy that reduces redundant nodes and (2) a fitness function that penalizes excessive leaf nodes, promoting smaller and more accurate decision trees. We perform a comparative performance analysis of these differential evolution variants, showing that while they exhibit similar statistical behavior, the Single-Objective real-parameter optimization (jSO) method produces the most accurate oblique decision trees and is second best in compactness. The findings highlight the potential of self-adaptive differential evolution algorithms to improve the effectiveness of oblique decision trees in machine learning applications.https://www.mdpi.com/2297-8747/29/6/103machine learningevolutionary computationexplainable artificial intelligence
spellingShingle Rafael Rivera-López
Efrén Mezura-Montes
Juana Canul-Reich
Marco-Antonio Cruz-Chávez
An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees
Mathematical and Computational Applications
machine learning
evolutionary computation
explainable artificial intelligence
title An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees
title_full An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees
title_fullStr An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees
title_full_unstemmed An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees
title_short An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees
title_sort experimental comparison of self adaptive differential evolution algorithms to induce oblique decision trees
topic machine learning
evolutionary computation
explainable artificial intelligence
url https://www.mdpi.com/2297-8747/29/6/103
work_keys_str_mv AT rafaelriveralopez anexperimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees
AT efrenmezuramontes anexperimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees
AT juanacanulreich anexperimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees
AT marcoantoniocruzchavez anexperimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees
AT rafaelriveralopez experimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees
AT efrenmezuramontes experimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees
AT juanacanulreich experimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees
AT marcoantoniocruzchavez experimentalcomparisonofselfadaptivedifferentialevolutionalgorithmstoinduceobliquedecisiontrees