PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 22, 2026Computer Methods in Biomechanics & Biomedical Engineering0 citations

Exercise ECG classification based on HRV features induced by robust R-peak detection model

View Full Paper
XSXinhua SuXWXuxuan WangHGHuanmin Ge

Key Result

The UNet-M-D model achieved up to 99.2% R-peak detection accuracy in noisy exercise ECGs and 77.4% accuracy in classifying exercise-induced fatigue using HRV features.

Key Points

  • The research aims to enhance exercise ECG classification accuracy using a robust R-peak detection model for HRV features.
  • Developed a UNet-M-D model integrating positional encoding, multi-head self-attention, and dynamic convolution.
  • Evaluated model performance on GUDB and EPFL datasets.
  • Measured R-peak detection accuracy and noise resilience using SNR metrics.
  • Achieved up to 99.2% accuracy in R-peak detection.
  • Demonstrated high noise resilience with performance in the range of 6-18 SNR.
  • Attained 77.4% accuracy in fatigue classification using optimally selected HRV features.

Structured PICO

Does the UNet-M-D model improve R-peak detection and fatigue classification accuracy in noisy exercise ECGs?

P
Population
Exercise ECGs from the GUDB and EPFL datasets
I
Intervention
UNet-M-D model (integrating positional encoding, multi-head self-attention, and dynamic convolution) for R-peak detection and HRV feature extraction
O
Outcome
R-peak detection accuracy and fatigue classification accuracysurrogate

The proposed UNet-M-D model provides highly accurate R-peak detection and fatigue classification in noisy exercise ECGs, offering a potential tool for sports health management.

Abstract

Exercise-induced fatigue assessment via ECG classification relies on accurate R-peak detection for reliable HRV features. Addressing the lack of robust models for noisy exercise ECGs, we propose UNet-M-D, integrating positional encoding, multi-head self-attention, and dynamic convolution. Evaluated on GUDB and EPFL datasets, it achieves superior R-peak detection performance (up to 99.2% accuracy) with high noise resilience (6-18 SNR). Using optimally selected HRV features, our method attains 77.4% accuracy in fatigue classification, providing a scientific basis for sports health management and training adjustment.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Su et al. (2026) studied this question. The UNet-M-D model achieved up to 99.2% R-peak detection accuracy in noisy exercise ECGs and 77.4% accuracy in classifying exercise-induced fatigue using HRV features.

synapsesocial.com/papers/699a9d14482488d673cd2c45https://doi.org/10.1080/10255842.2026.2629440
Ask AI
Helpful
Bookmark
Share
View Full Paper