# A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection

arXiv: https://arxiv.org/abs/2606.10410 · HTML: https://mlsanity.com/paper/2606.10410/

## 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 (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization](https://mlsanity.com/paper/2012.04456/) (2020)
- [Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks](https://mlsanity.com/paper/1706.00527/) (2017)
- [Multi-task Self-Supervised Learning for Human Activity Detection](https://mlsanity.com/paper/1907.11879/) (2019)
- [Understanding Test-Time Augmentation](https://mlsanity.com/paper/2402.06892/) (2024)
- [WildPPG: A Real-World PPG Dataset of Long Continuous Recordings](https://mlsanity.com/paper/2412.17540/) (2024)
- [GPT-PPG: A GPT-based Foundation Model for Photoplethysmography Signals](https://mlsanity.com/paper/2503.08015/) (2025)
- [Log-Spectral Matching GAN: PPG-based Atrial Fibrillation Detection can be Enhanced by GAN-based Data Augmentation with Integration of Spectral Loss](https://mlsanity.com/paper/2108.05272/) (2021)
- [Sparse learned kernels for interpretable and efficient medical time series processing](https://mlsanity.com/paper/2307.05385/) (2023)
- [BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averaging](https://mlsanity.com/paper/2406.17640/) (2024)
- [Towards physiology-informed data augmentation for EEG-based BCIs](https://mlsanity.com/paper/2203.14392/) (2022)
- [Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection using Eight Million Samples Labeled with Imprecise Arrhythmia Alarms](https://mlsanity.com/paper/2211.03333/) (2022)
- [SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals](https://mlsanity.com/paper/2404.15353/) (2024)
- [Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Data](https://mlsanity.com/paper/2309.09970/) (2023)
- [Comparative Analysis of Data Augmentation for Clinical ECG Classification with STAR](https://mlsanity.com/paper/2510.24740/) (2025)
- [A Novel Data Augmentation Strategy for Robust Deep Learning Classification of Biomedical Time-Series Data: Application to ECG and EEG Analysis](https://mlsanity.com/paper/2507.12645/) (2025)

## 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.