Evaluation of Resampling Techniques in CNN-Based Heartbeat Classification

• Published in: Ingénierie des systèmes d'Information Vol. 29; no. 4; pp. 1323 - 1332
• Main Authors: Subhiyakto, Egia Rosi, Rakasiwi, Sindhu, Zeniarja, Junta, Paramita, Cinantya, Shidik, Guruh Fajar, Hasibuan, Zainal Arifin, Kesić, Marijana Geets
• Format: Journal Article
• Language: English
• Published: Edmonton International Information and Engineering Technology Association (IIETA) 01.08.2024
• Subjects: Accuracy; Algorithms; Artificial neural networks; Cardiac arrhythmia; Cardiology; Cardiovascular disease; Classification; Datasets; Diagnostic systems; Electrocardiography; Feature recognition; Heart rate; Machine learning; Methods; Neural networks; Resampling; System effectiveness; Transformers

This study investigates the efficacy of resampling techniques in ECG classification, addressing the challenge of data imbalance in heartbeat classification. Utilizing the PTB Diagnostic ECG database, the research focuses on the application of various Synthetic Minority Over-sampling Technique (SMOTE...