Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance Enhancement

Advancements in machine learning have enabled the development of more accurate and efficient health prediction models. This study aims to improve diabetes prediction performance using the Support Vector Machine (SVM) model optimized with the Hybrid Gradient Descent Gray Wolf Optimizer (HGD-GWO) meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Sri Rossa Aisyah Puteri Baharie, Sugiyarto Surono, Aris Thobirin
Format: Article
Language:English
Published: Ikatan Ahli Informatika Indonesia 2025-02-01
Series:Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Subjects:
Online Access:https://jurnal.iaii.or.id/index.php/RESTI/article/view/6203
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850222626083962880
author Sri Rossa Aisyah Puteri Baharie
Sugiyarto Surono
Aris Thobirin
author_facet Sri Rossa Aisyah Puteri Baharie
Sugiyarto Surono
Aris Thobirin
author_sort Sri Rossa Aisyah Puteri Baharie
collection DOAJ
description Advancements in machine learning have enabled the development of more accurate and efficient health prediction models. This study aims to improve diabetes prediction performance using the Support Vector Machine (SVM) model optimized with the Hybrid Gradient Descent Gray Wolf Optimizer (HGD-GWO) method. SVM is a robust machine learning algorithm for classification and regression. Still, its performance depends significantly on selecting appropriate hyperparameters such as regularization (C), kernel coefficient (γ), and polynomial kernel degree (d). The HGD-GWO method synergizes gradient descent for local optimization and the Gray Wolf Optimizer for global solution exploration. Using the Pima Indians Diabetes dataset, the process includes normalization, hyperparameter optimization, data division, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The optimized SVM achieved an accuracy of 81.17%, with precision, recall, and F1-score values of 75.00%, 57.45%, and 65.06%, respectively, at a data ratio of 80%:20%. These findings highlight the potential of HGD-GWO in enhancing predictive models, particularly for early diabetes detection.
format Article
id doaj-art-e25f5f87f81c41e6aca85e85a1baecaf
institution OA Journals
issn 2580-0760
language English
publishDate 2025-02-01
publisher Ikatan Ahli Informatika Indonesia
record_format Article
series Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
spelling doaj-art-e25f5f87f81c41e6aca85e85a1baecaf2025-08-20T02:06:16ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602025-02-019114615210.29207/resti.v9i1.62036203Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance EnhancementSri Rossa Aisyah Puteri Baharie0Sugiyarto Surono1Aris Thobirin2Universitas Ahmad Dahlan Universitas Ahmad DahlanUniversitas Ahmad DahlanAdvancements in machine learning have enabled the development of more accurate and efficient health prediction models. This study aims to improve diabetes prediction performance using the Support Vector Machine (SVM) model optimized with the Hybrid Gradient Descent Gray Wolf Optimizer (HGD-GWO) method. SVM is a robust machine learning algorithm for classification and regression. Still, its performance depends significantly on selecting appropriate hyperparameters such as regularization (C), kernel coefficient (γ), and polynomial kernel degree (d). The HGD-GWO method synergizes gradient descent for local optimization and the Gray Wolf Optimizer for global solution exploration. Using the Pima Indians Diabetes dataset, the process includes normalization, hyperparameter optimization, data division, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The optimized SVM achieved an accuracy of 81.17%, with precision, recall, and F1-score values of 75.00%, 57.45%, and 65.06%, respectively, at a data ratio of 80%:20%. These findings highlight the potential of HGD-GWO in enhancing predictive models, particularly for early diabetes detection.https://jurnal.iaii.or.id/index.php/RESTI/article/view/6203hybrid gradient descent grey wolf optimizerhyperparameter optimizationdiabetes predictionmachine learningsupport vector machine (svm)
spellingShingle Sri Rossa Aisyah Puteri Baharie
Sugiyarto Surono
Aris Thobirin
Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance Enhancement
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
hybrid gradient descent grey wolf optimizer
hyperparameter optimization
diabetes prediction
machine learning
support vector machine (svm)
title Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance Enhancement
title_full Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance Enhancement
title_fullStr Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance Enhancement
title_full_unstemmed Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance Enhancement
title_short Hybrid Gradient Descent Grey Wolf Optimizer for Machine Learning Performance Enhancement
title_sort hybrid gradient descent grey wolf optimizer for machine learning performance enhancement
topic hybrid gradient descent grey wolf optimizer
hyperparameter optimization
diabetes prediction
machine learning
support vector machine (svm)
url https://jurnal.iaii.or.id/index.php/RESTI/article/view/6203
work_keys_str_mv AT srirossaaisyahputeribaharie hybridgradientdescentgreywolfoptimizerformachinelearningperformanceenhancement
AT sugiyartosurono hybridgradientdescentgreywolfoptimizerformachinelearningperformanceenhancement
AT aristhobirin hybridgradientdescentgreywolfoptimizerformachinelearningperformanceenhancement