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

Related Experiment Video

Updated: Jun 12, 2025

A Rat Model of Central Fatigue Using a Modified Multiple Platform Method

A Rat Model of Central Fatigue Using a Modified Multiple Platform Method

Published on: August 14, 2018

PCG-based exercise fatigue detection method using multi-scale feature fusion model.

Xinxin Ma¹, Xinhua Su¹, Huanmin Ge¹

¹School of Sports Engineering, Beijing Sports University, Beijing, China.

Computer Methods in Biomechanics and Biomedical Engineering

|September 25, 2024

Summary

This summary is machine-generated.

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

Post-processing correction of frequency sweep nonlinearity for FMCW LiDAR based on GPST-SST.

Applied optics·2026

Same author

Synthesis of Degradable Glycopolymers and Programming of Interfacial Hydrophobic Patches for Optimal TLR4-Mediated Immunity.

Biomacromolecules·2026

Same author

Ultrasound-Assisted Soaking Facilitates Purine Dissolution from Soybean Powder: Development and Preliminary Application of Low-Purine Soybean Powder.

Foods (Basel, Switzerland)·2026

Same author

Macrophage ALDH2 drives immunotherapy resistance by silencing CXCL9 through metabolic-epigenetic crosstalk.

Nature communications·2026

Same author

Enzyme/pH dual-stimuli responsive prochloraz nanopesticide controlled release system for kiwifruit soft rot disease control.

Pest management science·2026

Same author

Red Monascus pigments attenuate fructose-driven bovine serum albumin (BSA) glycation via non-covalent and covalent interactions with proteins.

Food chemistry·2026

Same journal

An interpretable, clinically-aligned AI paradigm for VTE risk prediction: an approach using LLMs and compound attention.

Computer methods in biomechanics and biomedical engineering·2026

Same journal

Effects of different resistance loads during resisted sprint running on internal stresses of the ankle joint: a finite element analysis.

Computer methods in biomechanics and biomedical engineering·2026

Same journal

Analysis of typical cases of medical infusion pump metering acceptance in nursing scenarios.

Computer methods in biomechanics and biomedical engineering·2026

Same journal

Investigation of biomechanical effect of inverted orthotic insoles on flexible flatfeet.

Computer methods in biomechanics and biomedical engineering·2026

Same journal

FeuNet: cross-user gesture recognition and fingertip force estimation network based on feature enhancement and U-Net.

Computer methods in biomechanics and biomedical engineering·2026

Same journal

Both chronological age and individual differences in aging are the two indispensable components for predicting biological age.

Computer methods in biomechanics and biomedical engineering·2026

See all related articles

This study introduces a new method for detecting exercise fatigue using Phonocardiogram (PCG) signals, offering a robust alternative to Electrocardiogram (ECG) monitoring. The novel approach achieves high accuracy in identifying fatigue levels.

Area of Science:

Biomedical Engineering
Physiological Monitoring
Machine Learning in Healthcare

Background:

Accurate exercise fatigue detection is crucial for safe physical activity.
Electrocardiogram (ECG) signals are commonly used but susceptible to noise.
Phonocardiogram (PCG) signals offer a non-invasive alternative for cardiovascular monitoring.

Purpose of the Study:

To propose a novel Phonocardiogram (PCG)-based method for detecting exercise fatigue.
To enhance fatigue detection performance through feature fusion of deep learning and linear features.
To evaluate the proposed method's accuracy and compare it with ECG-based systems.

Main Methods:

1D PCG signals were converted to 2D images using Short-Time Fourier Transform (STFT).

Keywords:

PCG STFT VGG future fusion

More Related Videos

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test

Published on: July 27, 2015

Related Experiment Videos

Last Updated: Jun 12, 2025

A Rat Model of Central Fatigue Using a Modified Multiple Platform Method

A Rat Model of Central Fatigue Using a Modified Multiple Platform Method

Published on: August 14, 2018

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test

Determining The Electromyographic Fatigue Threshold Following a Single Visit Exercise Test

Published on: July 27, 2015

A pre-trained Convolutional Neural Network (VGG-16) was used for deep learning feature extraction.

Fusion features were created by combining VGG-16 features with PCG linear features.

Support Vector Machines (SVM) and Linear Discriminant Analysis (LDA) were employed for fatigue classification.

Main Results:

The proposed PCG-based method achieved high accuracy (up to 99.00%) and F1-score (up to 99.09%).
Performance was comparable to traditional ECG-based systems, considered the gold standard.
The method demonstrated effectiveness in distinguishing six levels of exercise fatigue.

Conclusions:

Phonocardiogram (PCG) signals can be effectively utilized for accurate exercise fatigue detection.
The proposed feature fusion technique significantly improves fatigue detection performance.
This non-invasive PCG-based approach presents a promising alternative for exercise monitoring.