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

Classification of Signals01:30

Classification of Signals

1.1K
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...
1.1K
Force Classification01:22

Force Classification

1.9K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.9K

You might also read

Related Articles

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

Sort by
Same author

Ultrahigh-energy gamma-ray emission associated with black hole-jet systems.

National science review·2025
Same author

Dietary Sarcodia suieae hydrocolloid supplementation elevates quercetin levels and modulates metabolic and immune pathways in the hepatopancreas of Macrobrachium rosenbergii: Insights from integrated omics analyses.

Developmental and comparative immunology·2025
Same author

Transcriptome profile of early matured Macrobrachium rosenbergii (Giant Freshwater Prawn) from Taiwan.

Scientific data·2025
Same author

Artificial Intelligence and Deep Learning in Sensors and Applications: 2nd Edition.

Sensors (Basel, Switzerland)·2025
Same author

Using Infrared Raman Spectroscopy with Machine Learning and Deep Learning as an Automatic Textile-Sorting Technology for Waste Textiles.

Sensors (Basel, Switzerland)·2025
Same author

Characteristics of <i>Gracilariopsis lemaneiformis</i> hydrocolloids and their effects on intestine PPAR signaling and liver lipid metabolism in <i>Oreochromis niloticus</i>: A multiomics analysis.

Heliyon·2024

Related Experiment Video

Updated: Nov 7, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

150

Efficiently Classifying Lung Sounds through Depthwise Separable CNN Models with Fused STFT and MFCC Features.

Shing-Yun Jung1, Chia-Hung Liao1, Yu-Sheng Wu1

  • 1Department of Computer Science, National Chiao Tung University, Hsinchu 300, Taiwan.

Diagnostics (Basel, Switzerland)
|April 30, 2021
PubMed
Summary

Combining Short-Time Fourier Transform (STFT) and Mel-frequency cepstral coefficient (MFCC) features improves AI accuracy for classifying lung sounds. This approach enables efficient, AI-aided lung disease detection on edge devices.

Keywords:
automatic auscultationsconvolutional neural networkdepthwise separable convolutionfeature extractionlung sounds

More Related Videos

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

621
Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

531

Related Experiment Videos

Last Updated: Nov 7, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

150
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

621
Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

531

Area of Science:

  • Medical Diagnostics
  • Artificial Intelligence
  • Signal Processing

Background:

  • Lung sounds are crucial for diagnosing pulmonary conditions.
  • The COVID-19 pandemic highlights the need for advanced AI in lung auscultation.
  • Accurate and efficient lung sound classification is essential for clinical practice.

Purpose of the Study:

  • To develop a feature engineering process for AI-based lung sound classification.
  • To optimize the depthwise separable convolution neural network (DS-CNN) for lung sound analysis.
  • To enhance the accuracy and efficiency of AI-aided lung disease detection.

Main Methods:

  • Extracted Short-Time Fourier Transform (STFT) and Mel-frequency cepstral coefficient (MFCC) features from lung sounds.
  • Engineered fused features combining STFT and MFCC.
  • Trained a depthwise separable convolution neural network (DS-CNN) using these features.

Main Results:

  • DS-CNN with fused STFT and MFCC features achieved 85.74% accuracy.
  • Individual STFT and MFCC features yielded accuracies of 82.27% and 73.02%, respectively.
  • The proposed method demonstrated 16x faster inference speed on edge devices compared to RespireNet with minimal accuracy loss (0.45%).

Conclusions:

  • Fusing STFT and MFCC features with DS-CNN enhances lung sound classification accuracy.
  • This model design is suitable for lightweight edge devices for AI-aided lung disease detection.
  • The approach offers a promising solution for efficient and accurate remote or point-of-care diagnostics.