خولی چوارەمی پێداگۆجی بۆ مامۆستایانی وەزارەتی پەروەردە لە زانكۆی جیهان – سلێمانی دەستی پێكرد
Assistant Lecturer Sherko Hamalaw from the Department of Computer Science and Researcher Nozad Hussein Mahmood, the Director of the Biostatistics Consulting Department at the Research Center, have published a research paper in an international journal, “MethodX,” titled “Hybrid Genetic Algorithms-Driven Optimization of Machine Learning Models for Heart Disease Prediction.”
In this study, machine learning (ML) models, such as K-Nearest Neighbor (KNN) and Support Vector Machine (SVM), were used to predict heart disease. However, their performance is often limited by poor hyperparameter selection. This study presents a novel hybrid approach that utilizes a Genetic Algorithm (GA) to systematically optimize the hyperparameters of KNN and SVM models, resulting in improved classification outcomes. The optimization driven by the GA resulted in significant performance improvements, increasing the classification accuracy of KNN to 95.38% and SVM to 90%. Furthermore, there were significant improvements in precision, recall, and F-score. Our findings demonstrate that GA-based hyperparameter tuning is an effective strategy for improving the predictive power and clinical relevance of ML models used for heart disease classification.
GA Driven Optimization: Genetic algorithm was utilized to fine-tune the hyperparameters of K-Nearest Neighbour (KNN) and Support Vector Machine (SVM) classifiers for improved performance.
Significant Performance Gains: The optimization process aimed to maximize classification across metrics such as accuracy, precision, recall, and F-score.
Improved Accuracy: The GA-based tuning significantly increased the classification accuracy, improving KNN to 95.38% and SVM to 90%.
The journal is indexed in Scopus (Q2) and has an impact factor =1.9.
The article can be found at the following link: https://doi.org/10.1016/j.mex.2025.103510
Related posts
