Evaluating the Performance of Naïve Bayes and Support Vector Machine Classifiers for Diabetes Classification Using Cross-Validation
Computer Journal · 01.02.2027 · 5 (1) · 123-131
DOI: 10.58477/cj.v5i1.595 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Journal, online erschienen am 01.02.2027. Verfasst von Zainudin Zainudin und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Diabetes mellitus
Abstract (Originalsprache)
This study aims to compare the performance of the Naïve Bayes and Support Vector Machine algorithms in diabetes classification using the Pima Indians Diabetes Database. The dataset consists of 768 observations with eight predictor attributes and one target attribute, namely Outcome. The research methodology includes data understanding, preprocessing, model training, and evaluation using Stratified 10-Fold Cross-Validation. Preprocessing encompasses handling zero values on certain attributes, median imputation, and feature standardization for SVM. Evaluation was carried out using accuracy, precision, recall, F1-score, ROC-AUC, and a confusion matrix. The test results showed that SVM obtained an average accuracy of 0.7474, precision of 0.6805, recall of 0.5373, F1-score of 0.5969, and ROC-AUC of 0.8256. Meanwhile, Naïve Bayes obtained an average accuracy of 0.7460, precision of 0.6610, recall of 0.6010, F1-score of 0.6222, and ROC-AUC of 0.8128. Based on the confusion matrix, Naïve Bayes correctly classified 161 of the 268 diabetes samples, whereas SVM correctly classified 144 samples. The results indicate that SVM achieved slightly higher accuracy and ROC-AUC, whereas Naïve Bayes provided better recall and F1-score values, demonstrating a superior capability in recognizing diabetes samples in this test. Consequently, algorithm selection must consider classification objectives and evaluation metrics, particularly when detecting the diabetes class is a priority.
Zitieren
APA
Zainudin, Z., & Fahmi, A. (2027). Evaluating the Performance of Naïve Bayes and Support Vector Machine Classifiers for Diabetes Classification Using Cross-Validation. Computer Journal, 5(1), 123-131. https://doi.org/10.58477/cj.v5i1.595
Vancouver
Zainudin Z, Fahmi A. Evaluating the Performance of Naïve Bayes and Support Vector Machine Classifiers for Diabetes Classification Using Cross-Validation. Computer Journal. 2027;5(1):123-131. doi:10.58477/cj.v5i1.595
BibTeX
@article{Zainudin2027,
author = {Zainudin, Zainudin and Fahmi, Andri},
title = {Evaluating the Performance of Naïve Bayes and Support Vector Machine Classifiers for Diabetes Classification Using Cross-Validation},
journal = {Computer Journal},
year = {2027},
volume = {5},
number = {1},
pages = {123--131},
doi = {10.58477/cj.v5i1.595}
}
EUVIMED