Manuscript received April 23, 2025; revised May 22, 2025; accepted June 30, 2025; published October 17, 2025.

Abstract—Arrhythmia is a condition characterised by irregularities in heart rhythm, where the heartbeat may be excessively fast, abnormally slow, or irregular, potentially leading to severe complications such as heart attacks or sudden cardiac death. Accurate diagnosis of Arrhythmia is essential, but it has traditionally relied on Electrocardiogram (ECG) analysis by medical experts, which can be timeconsuming and subject to variability. In recent years, computational methods have gained prominence in arrhythmia classification, improving diagnostic speed, accuracy, and automation. This study investigates the effectiveness of machine learning models, namely Random Forest (RF), Support Vector Machine (SVM), and Adaptive Boosting (AdaBoost), in classifying arrhythmias using features extracted from ECG signals through Discrete Wavelet Transform (DWT). The dataset was sourced from the Massachusetts Institute of Technology—Beth Israel Hospital Arrhythmia Database, and the research involved several stages, including data collection, preprocessing, feature extraction, model training, and performance evaluation. The results indicate that RF achieves the highest accuracy at 97.50%, SVM at 97.20%, and AdaBoost at 90.20%. These findings demonstrate the superior performance of RF in handling arrhythmia classification tasks, highlighting its potential for enhancing automated ECG interpretation and assisting in early diagnosis and clinical decision-making.

Keywords—Discrete Wavelet Transform (DWT), arrhythmia database, Random Forest (RF), Support Vector Machine (SVM), Adaptive Boosting (AdaBoost)

Cite: Melinda Melinda, Muhammad Raja, Junidar Junidar, Rizka Miftahujjannah, Siti Rusdiana, and Muhammad Irhamsyah, "Performance Comparison Analysis of Random Forest, Support Vector Machine, and AdaBoost in Arrhythmia Classification," Journal of Image and Graphics, Vol. 13, No. 5, pp. 540-548, 2025.

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC-BY-4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.