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

Heart Sounds01:15

Heart Sounds

2.0K
Heart sounds are generated by the turbulence in blood flow due to the closing of heart valves. These sounds are best perceived slightly away from the valves, where the blood flow disseminates the sound.
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V)...
2.0K
Classification of Signals01:30

Classification of Signals

529
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...
529

You might also read

Related Articles

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

Sort by
Same author

[A study on heart sound classification algorithm based on improved Mel-frequency cepstrum coefficient feature extraction and deep Transformer].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2025
Same author

[Application of multi-scale spatiotemporal networks in physiological signal and facial action unit measurement].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2025
Same author

Multi-Omics Integration Analysis Pinpoint Proteins Influencing Brain Structure and Function: Toward Drug Targets and Neuroimaging Biomarkers for Neuropsychiatric Disorders.

International journal of molecular sciences·2024
Same author

3-D-Gaze-Based Robotic Grasping Through Mimicking Human Visuomotor Function for People With Motion Impairments.

IEEE transactions on bio-medical engineering·2017
Same author

Hybrid Perovskite Light-Emitting Diodes Based on Perovskite Nanocrystals with Organic-Inorganic Mixed Cations.

Advanced materials (Deerfield Beach, Fla.)·2017
Same author

Merocyclophanes C and D from the Cultured Freshwater Cyanobacterium Nostoc sp. (UIC 10110).

Journal of natural products·2017

Related Experiment Video

Updated: Jul 18, 2025

Behavioral Determination of Stimulus Pair Discrimination of Auditory Acoustic and Electrical Stimuli Using a Classical Conditioning and Heart-rate Approach
10:50

Behavioral Determination of Stimulus Pair Discrimination of Auditory Acoustic and Electrical Stimuli Using a Classical Conditioning and Heart-rate Approach

Published on: June 6, 2012

14.6K

A learnable front-end based efficient channel attention network for heart sound classification.

Aolei Liu1, Sunjie Zhang1, Zhe Wang1

  • 1School of Optical Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, People's Republic of China.

Physiological Measurement
|August 24, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an Efficient Channel Attention Network (ECA-Net) with a learnable front-end for improved heart sound classification accuracy. The novel approach achieves 97.77% accuracy, surpassing traditional methods by adaptively extracting features.

Keywords:
convolutional recurrent neuralefficient channel attention networkfeature extractionheart sound classificationlearnable front-end

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
Semi-automated Optical Heartbeat Analysis of Small Hearts
12:10

Semi-automated Optical Heartbeat Analysis of Small Hearts

Published on: September 16, 2009

12.3K

Related Experiment Videos

Last Updated: Jul 18, 2025

Behavioral Determination of Stimulus Pair Discrimination of Auditory Acoustic and Electrical Stimuli Using a Classical Conditioning and Heart-rate Approach
10:50

Behavioral Determination of Stimulus Pair Discrimination of Auditory Acoustic and Electrical Stimuli Using a Classical Conditioning and Heart-rate Approach

Published on: June 6, 2012

14.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
Semi-automated Optical Heartbeat Analysis of Small Hearts
12:10

Semi-automated Optical Heartbeat Analysis of Small Hearts

Published on: September 16, 2009

12.3K

Area of Science:

  • Cardiology
  • Biomedical Engineering
  • Artificial Intelligence in Medicine

Background:

  • Traditional heart sound classification models often rely on handcrafted features, which can lead to information loss and require extensive parameter tuning.
  • Limitations in current models hinder the accurate identification of pathological information within heart sounds.

Purpose of the Study:

  • To develop an advanced heart sound classification model that overcomes the limitations of handcrafted feature extraction.
  • To improve the accuracy and efficiency of automated heart sound analysis using deep learning.

Main Methods:

  • A novel learnable front-end was integrated with an Efficient Channel Attention Network (ECA-Net) for adaptive feature extraction from waveform-to-spectrogram transformations.
  • A convolutional recurrent neural network architecture utilizing ECA-Net was employed to emphasize relevant features and mitigate noise.
  • Focal loss was incorporated to address data imbalance issues inherent in medical datasets.

Main Results:

  • The proposed ECA-Net based model achieved a high classification accuracy of 97.77% on the PhysioNet challenge 2016 dataset.
  • This performance significantly outperformed most previous studies and closely approached the top-performing models.
  • The learnable front-end enabled effective end-to-end training, replacing conventional feature extraction modules.

Conclusions:

  • The developed learnable front-end ECA-Net offers a novel and efficient solution for heart sound classification.
  • This approach enhances the practical application of end-to-end deep learning models in cardiovascular diagnostics.
  • The method demonstrates potential for improving the accuracy and reliability of automated cardiac auscultation.