Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Home
A Comprehensive Inference-time Augmentation Framework In Physiological Signals: Application To Ppg-based Af Detection.

Home
A Comprehensive Inference-time Augmentation Framework In Physiological Signals: Application To Ppg-based Af Detection.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

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

ArXiv·2026

Same author

Predicting Post-Radiotherapy Epigenetic Age Acceleration From Pre-Treatment Data Using a Machine Learning Framework in Head and Neck Cancer Patients.

Cancer medicine·2026

Same author

Rethinking airborne transmission risk of monkeypox virus: a methodological perspective on quantitative PCR threshold collapse in environmental air sampling.

The Lancet. Microbe·2026

Same author

ADAN: Adversarial Distribution Alignment Network for Multi-View Semi-Supervised Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Infectious respiratory particles exhaled by Clade IIb Mpox virus-infected macaques.

Emerging microbes & infections·2026

Same author

The globally prevalent MPXV strain exhibits high airborne and contact transmissibility in black-tailed prairie dogs.

Emerging microbes & infections·2026

Same journal

Dissecting the integrated information of cardiovascular and cardiorespiratory systems at rest and during physiological stress.

Physiological measurement·2026

Same journal

Respiratory event type and duration modulate PPG waveforms in OSA.

Physiological measurement·2026

Same journal

Estimating changes in systolic blood pressure based on pulse wave morphology using paired segment comparison.

Physiological measurement·2026

Same journal

Small changes in hand height alter absorbance, but not pulsation, in the finger pulse plethysmograph.

Physiological measurement·2026

Same journal

Quantification of pendelluft in electrical impedance tomography data: opening Pandora's box? A literature review of analytical methods.

Physiological measurement·2026

Same journal

An intelligent evaluation model for spirometry quality using wavelet and deep time-series methods.

Physiological measurement·2026

See all related articles

Related Experiment Video

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

Published on: April 26, 2024

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

Davood Fattahi¹, Runze Yan², Saurabh Kataria³

¹Emory University, 1520 Clifton Rd N E, Atlanta, GA 30322, Atlanta, Georgia, 30322, United States.

Physiological Measurement

|June 15, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

This study introduces a unified inference-time augmentation (ITA) framework to enhance the accuracy of physiological signal classification, particularly for atrial fibrillation detection using photoplethysmography (PPG) signals.

Keywords:

artificial intelligence atrial fibrillation detection inference time augmentation photoplethysmography physiological signals

More Related Videos

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Published on: November 14, 2017

Related Experiment Videos

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

Published on: April 26, 2024

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Published on: November 14, 2017

Area of Science:

Biomedical Engineering
Signal Processing
Machine Learning

Background:

Physiological signal classification faces challenges like noise and data shifts in real-world use.
Inference-time augmentation (ITA) improves robustness but has been limited in scope for physiological signals.
Existing ITA methods use few augmentations with unoptimized parameters.

Purpose of the Study:

To propose a unified inference-time augmentation (ITA) framework for physiological signals.
To systematically optimize ITA hyperparameters using Bayesian optimization.
To enhance the reliability of atrial fibrillation (AF) detection from photoplethysmography (PPG) signals.

Main Methods:

Developed a framework with 13 augmentation methods (time, amplitude, frequency, artifact injection).
Employed Bayesian optimization for systematic hyperparameter tuning.
Evaluated on AF detection using GPT-PPG and ResNet models across five PPG datasets (~9,800 hours).

Main Results:

Standard ITA improved AUROC (up to 8.5%) and AUPRC (up to 10.6%) across models and datasets.
Selective ITA reduced false positive rates (FPR) by up to 4.4% on non-AF datasets.
Consistent performance gains observed for both GPT-PPG and ResNet architectures.

Conclusions:

ITA is a practical, model-agnostic method for improving PPG-based AF classification in deployment.
The unified framework enhances robustness against noise and data shifts without retraining.
Findings support broader application of ITA in physiological signal analysis.