A Comparative Analysis of Supervised and Unsupervised Learning Methods for Normal-Abnormal Heartbeat Classification
Cicek, B.; Ozturk, F.; Erdem, Y. E.; Sayin, I.; Sarialioglu, O.; Balci, I. C.; Beser, S.; Uvet, H.; Sayin, I.
Show abstract
In this study, the performances of 33 supervised and unsupervised machine learning methods for the automatic classification of cardiac arrhythmias as normal or abnormal using the MIT BIH Arrhythmia Database are evaluated. Electrocardiogram signals from the MLII and V1 leads are segmented into fixed-length windows aligned to the R peak, with raw amplitude values used as model inputs without feature extraction. In the supervised analysis, various statistical and ensemble classifiers are evaluated, while the unsupervised analysis assesses Isolation Forest, One Class support vector machines (SVM), Local Outlier Factor, Elliptic Envelope, and an autoencoder model. The results demonstrate that, when labeled data are available, supervised methods, particularly K nearest neighbors (KNN) and Random Forest, provide higher accuracy and more balanced classification compared with unsupervised models. Unsupervised approaches, on the other hand, are positioned as complementary tools for arrhythmia screening and early warning when labeled data are limited.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Digitizing ECG image: new fully automated method and open-source software code 97%
- An algorithm to detect dicrotic notch in arterial blood pressure and photoplethysmography waveforms using the iterative envelope mean method 96%
- BRAVEHEART: Open-source software for automated electrocardiographic and vectorcardiographic analysis 96%
Similar papers in this journal
- Ventricular anatomical complexity and gender differences impact predictions from computational models 96%
- Quantitative assessment of the relationship between behavioral and autonomic dynamics during propofol-induced unconsciousness 95%
- A Signal Demodulation-based Method for the Early Detection of Cheyne-Stokes Respiration 95%
Similar papers in this journal
- An Open-Access Simultaneous Electrocardiogram and Phonocardiogram Database 96%
- Comparison of feature-based indices derived from photoplethysmogram recorded from different body locations during lower body negative pressure 96%
- Classification of 12-lead ECGs: the PhysioNet/Computing in Cardiology Challenge 2020 94%
Similar papers in this journal
Similar papers in this journal
- Hilbert-Envelope Features for Cardiac Disease Classification from Noisy Phonocardiograms 96%
- Improved online event detection and differentiation by a simple gradient-based nonlinear transformation: Implications for the biomedical signal and image analysis 95%
- Evaluating three different adaptive decomposition methods for EEG signal seizure detection and classification 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.