A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection
Not on the map. Why?
Abstract (arXiv)
Objective: Accurate classification of physiological signals in real-world deployments is challenged by sensor noise, motion artifacts, and distribution shifts between training and deployment data. Inference-time augmentation (ITA), which applies augmentations during inference rather than retraining, offers a simple, model-agnostic mechanism to improve robustness. However, ITA application to physiological signals has remained narrow in scope, relying on limited augmentation methods with fixed, unoptimized parameters. This work proposes a unified ITA framework to address that gap. Approach: The framework incorporates 13 augmentation methods spanning time-domain, amplitude-domain, frequency-domain, and artifact-injection transformations, with hyperparameters optimized via Bayesian optimization. We evaluate on atrial fibrillation (AF) detection from 30-second PPG signals using GPT-PPG and ResNet across five datasets comprising more than 400 patients and ~9,800 hours of recording. Main results: Standard ITA consistently improved AUROC (up to 8.5% for GPT-PPG and 0.7% for ResNet) and AUPRC (up to 10.6% for GPT-PPG and 0.8% for ResNet). Selective ITA further reduced average FPR by up to 4.4% (GPT-PPG) and 1.3% (ResNet) on non-AF datasets. Significance: These findings establish ITA as a practical, model-agnostic approach for improving PPG-based AF classification reliability in deployment settings where retraining is not feasible, with broader applicability to physiological signal analysis.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 54 references that are in the map. First posted on arXiv 9 Jun 2026.
Builds on
16 of 54 references.
References · 16
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualizationcited by 173
- 2017Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networkscited by 131
- 2019Multi-task Self-Supervised Learning for Human Activity Detectioncited by 102
- 2024Understanding Test-Time Augmentationcited by 23
- 2024WildPPG: A Real-World PPG Dataset of Long Continuous Recordingscited by 15
- 2025GPT-PPG: A GPT-based Foundation Model for Photoplethysmography Signalscited by 15
- 2021Log-Spectral Matching GAN: PPG-based Atrial Fibrillation Detection can be Enhanced by GAN-based Data Augmentation with Integration of Spectral Losscited by 7
- 2023Sparse learned kernels for interpretable and efficient medical time series processingcited by 6
- 2024BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averagingcited by 5
- 2022Towards physiology-informed data augmentation for EEG-based BCIscited by 4
- 2022Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection using Eight Million Samples Labeled with Imprecise Arrhythmia Alarmscited by 4
4 more
- 2024SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signalscited by 4
- 2023Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Datacited by 3
- 2025Comparative Analysis of Data Augmentation for Clinical ECG Classification with STARcited by 3
- 2025A Novel Data Augmentation Strategy for Robust Deep Learning Classification of Biomedical Time-Series Data: Application to ECG and EEG Analysiscited by 2
Built on by
Not cited yet.