New Test-Time Scenario for Biosignal: Concept and Its Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jo, Yong-Yeon, Lee, Byeong Tak, Kim, Beom Joon, Hong, Jeong-Ho, Lee, Hak Seung, Kwon, Joon-myoung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909406025744384
author Jo, Yong-Yeon
Lee, Byeong Tak
Kim, Beom Joon
Hong, Jeong-Ho
Lee, Hak Seung
Kwon, Joon-myoung
author_facet Jo, Yong-Yeon
Lee, Byeong Tak
Kim, Beom Joon
Hong, Jeong-Ho
Lee, Hak Seung
Kwon, Joon-myoung
contents Online Test-Time Adaptation (OTTA) enhances model robustness by updating pre-trained models with unlabeled data during testing. In healthcare, OTTA is vital for real-time tasks like predicting blood pressure from biosignals, which demand continuous adaptation. We introduce a new test-time scenario with streams of unlabeled samples and occasional labeled samples. Our framework combines supervised and self-supervised learning, employing a dual-queue buffer and weighted batch sampling to balance data types. Experiments show improved accuracy and adaptability under real-world conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17785
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle New Test-Time Scenario for Biosignal: Concept and Its Approach
Jo, Yong-Yeon
Lee, Byeong Tak
Kim, Beom Joon
Hong, Jeong-Ho
Lee, Hak Seung
Kwon, Joon-myoung
Signal Processing
Machine Learning
Online Test-Time Adaptation (OTTA) enhances model robustness by updating pre-trained models with unlabeled data during testing. In healthcare, OTTA is vital for real-time tasks like predicting blood pressure from biosignals, which demand continuous adaptation. We introduce a new test-time scenario with streams of unlabeled samples and occasional labeled samples. Our framework combines supervised and self-supervised learning, employing a dual-queue buffer and weighted batch sampling to balance data types. Experiments show improved accuracy and adaptability under real-world conditions.
title New Test-Time Scenario for Biosignal: Concept and Its Approach
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2411.17785