ECG Monitoring and Analysis

Towards a Physiological Scaling Law: Model Quality vs. Cohort Size for Stochastic Sequence Data

The paper evaluates scaling laws for stochastic sequence data using distributional calibration metrics, showing that performance improves with cohort size beyond point accuracy saturation.

Evaluating Long-Range Temporal Structure in Foundation Model-Based Forecasts of Heartbeat Dynamics

This study evaluates how well Time-Series Foundation Models predict heartbeat dynamics and finds they fail to capture long-range temporal dependencies, leading to increasing prediction errors over time.

QRS Detection by Combinatorial Optimization With MLP Assisted Peak Scoring

This paper introduces a QRS detector using MLP-assisted peak scoring and combinatorial optimization, achieving high sensitivity and PPV in noisy signals.

Use of deep learning algorithms for segmentation of microelectrode arrays electrograms in the study of changes in myocardial bioelectrical activity

The paper uses a U-Net-based neural network to segment electrograms from microelectrode arrays in rat hearts perfused with L-carnitine, showing reduced heart rate and conduction velocity.

Modeling Electrocardogram (ECG) Waveforms Using Group Theory and Symmetry Elements

The paper introduces a novel method using group theory and symmetry elements to generate ECG waveforms without predefined boundary conditions, offering a new perspective on biological signal representation.

Deep Learning-Based Inference of Uterine Contractions from Maternal ECG

This paper develops a deep learning algorithm to infer uterine contractions from maternal ECGs, achieving a Pearson correlation coefficient of 0.53 with ground truth data.

Learning Discriminative Representations of Superimposed P waves With Weakly-Supervised Temporal Contrastive Learning

This paper introduces S-TCRL, a weakly-supervised framework for learning discriminative representations of superimposed P waves in ECG signals, achieving improved segmentation performance.

Electrocardiogram feature extraction and interval measurements using optimal representative cycles from persistent homology

This paper introduces a topological method to identify ECG waves and measure intervals using optimal representative cycles from persistent homology, showing utility in arrhythmia detection.

Digitization of Electrocardiogram Using Bilateral Filtering

This paper proposes a bilateral filtering method to digitize printed ECG graph sheets, preserving peak amplitude characteristics for accurate diagnosis and database creation.

Quadratic Programming Data Descriptors for Abnormal Beat Detection in ECG Recordings

This paper introduces a novel one-class classifier for abnormal beat detection in ECG using wavelet domain features and evaluates it on the MIT-BIH arrhythmia database.