Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

665
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
665
Deconvolution01:20

Deconvolution

236
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
236
Classification of Signals01:30

Classification of Signals

734
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
734
Reducing Line Loss01:18

Reducing Line Loss

188
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
188
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.8K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
6.8K

You might also read

Related Articles

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

Sort by
Same author

Inter-patient multi-label ECG classification via low-rank adaptation fine-tuned large language models with dynamic graph convolutional network.

Physiological measurement·2026
Same author

An Artificial Intelligence QRS Detection Algorithm for Wearable Electrocardiogram Devices.

Micromachines·2025
Same author

Blood Pressure Estimation Based on PPG and ECG Signals Using Knowledge Distillation.

Cardiovascular engineering and technology·2024
Same author

Prediction of Sleep Apnea Events Using a CNN-Transformer Network and Contactless Breathing Vibration Signals.

Bioengineering (Basel, Switzerland)·2023
Same author

A Multi-Parameter Fusion Method for Cuffless Continuous Blood Pressure Estimation Based on Electrocardiogram and Photoplethysmogram.

Micromachines·2023
Same author

An Arrhythmia Classification Model Based on Vision Transformer with Deformable Attention.

Micromachines·2023

Related Experiment Video

Updated: Aug 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

A lightweight U-net for ECG denoising using knowledge distillation.

Lishen Qiu1,2, Miao Zhang2, Wenliang Zhu1,2

  • 1School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, People's Republic of China.

Physiological Measurement
|September 30, 2022
PubMed
Summary

This study introduces a lightweight deep learning model for electrocardiogram (ECG) denoising, significantly improving signal quality and enabling real-time applications. The enhanced model effectively removes noise while preserving crucial ECG waveform details.

Keywords:
ECGULde-netdeep learningdenoisinglightweight

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

Related Experiment Videos

Last Updated: Aug 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence in Healthcare
  • Signal Processing

Background:

  • Electrocardiogram (ECG) signals are susceptible to noise, which can impair diagnostic accuracy.
  • Deep learning models for ECG denoising often face challenges with computational complexity, limiting real-time application.
  • Lightweight model design is crucial for deploying advanced signal processing techniques in resource-constrained environments.

Purpose of the Study:

  • To develop a computationally efficient and lightweight deep learning model for effective ECG signal denoising.
  • To improve the practical applicability of deep learning-based ECG denoising methods in real-time scenarios.
  • To maintain high denoising performance while reducing model complexity.

Main Methods:

  • A novel U-net architecture combining grouped and depthwise convolutions for feature compression and efficient processing.
  • Integration of identity connections and a local maximum and minimum enhancement module to preserve ECG waveform details.
  • Application of knowledge distillation to further enhance denoising performance without increasing model complexity.
  • Utilized datasets from CPSC 2018 for ground-truth ECG and NSTDB for noise signals.
  • Performance evaluation using Signal-to-Noise Ratio (SNR), Root Mean Square Error (RMSE), and Pearson correlation coefficient (P).

Main Results:

  • The proposed U-net model achieved significant improvements in SNR (10.30-12.61 dB), reductions in RMSE (9.88-20.63 × 10⁻²), and increases in P (14.77-27.74 × 10⁻²).
  • Knowledge distillation further boosted denoising performance.
  • The U-net model demonstrated remarkable efficiency with only 6.9K parameters and 6.6M FLOPs, significantly lower than comparative models.
  • Experimental results validated across different data generation groups.

Conclusions:

  • The developed lightweight U-net model effectively denoises ECG signals while preserving essential waveform characteristics.
  • The model's reduced computational complexity makes it suitable for real-time ECG processing applications.
  • This approach offers a practical solution for ECG denoising in environments with limited time or memory resources.