Clustering and Visualization of ECG Signals

Vágner, Anikó; Farkas, László; Juhász, István

doi:10.1007/978-3-642-23163-6_7

Cited by 4 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We hypothesize that the clustering-based approach in SwAV might have allowed the model to learn more robust and diverse representations that capture the essential and generalizable features of the ECG signals, leading to better performance. Clustering can be especially effective in cases where there are different underlying structures in the data, as it can help to identify this structure and improve the quality of the learned representations [36,37,38].…”

Section: B Ssl Methods Performancementioning

confidence: 99%

Analysis of Augmentations for Contrastive ECG Representation Learning

Soltanieh¹,

Etemad²,

Hashemi

2022

2022 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

This paper presents a systematic investigation into the effectiveness of Self-Supervised Learning (SSL) methods for Electrocardiogram (ECG) arrhythmia detection. We begin by conducting a novel distribution analysis on three popular ECGbased arrhythmia datasets: PTB-XL, Chapman, and Ribeiro. To the best of our knowledge, our study is the first to quantify these distributions in this area. We then perform a comprehensive set of experiments using different augmentations and parameters to evaluate the effectiveness of various SSL methods, namely SimCRL, BYOL, and SwAV, for ECG representation learning, where we observe the best performance achieved by SwAV. Furthermore, our analysis shows that SSL methods achieve highly competitive results to those achieved by supervised stateof-the-art methods. To further assess the performance of these methods on both In-Distribution (ID) and Out-of-Distribution (OOD) ECG data, we conduct cross-dataset training and testing experiments. Our comprehensive experiments show almost identical results when comparing ID and OOD schemes, indicating that SSL techniques can learn highly effective representations that generalize well across different OOD datasets. This finding can have major implications for ECG-based arrhythmia detection. Lastly, to further analyze our results, we perform detailed perdisease studies on the performance of the SSL methods on the three datasets.

show abstract

Section: B Ssl Methods Performancementioning

confidence: 99%