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 Experiment Video

Updated: Oct 31, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.8K

Deep Learning Assisted Neonatal Cry Classification via Support Vector Machine Models.

Ashwini K1, P M Durai Raj Vincent1, Kathiravan Srinivasan1

  • 1School of Information Technology and Engineering, Vellore Institute of Technology (VIT), Vellore, India.

Frontiers in Public Health
|June 28, 2021
PubMed
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

Novel deep learning solutions with layered recurrent neural networks for nonlinear stiff Dahl hysteresis model in piezoelectric actuator.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Predictive analysis of plankton population dynamics in marine biosphere: a nonlinear ARX neural network for the carbon-thermal-nutrient-plankton asymmetric multifactor system for global warming.

Environmental monitoring and assessment·2025
Same author

Artificial intelligence for fall detection in older adults: A comprehensive survey of machine learning, deep learning approaches, and future directions.

Ageing research reviews·2025
Same author

A Robust and Efficient Workflow for Heart Valve Disease Detection from PCG Signals: Integrating WCNN, MFCC Optimization, and Signal Quality Evaluation.

Sensors (Basel, Switzerland)·2025
Same author

Neuro-computational surrogates for aqueous fractional-order nekton-plankton spatiotemporal dynamics under toxicant stress, refuge efficacy, and nutrient flux modulation.

Water research·2025
Same author

Feature-Shuffle and Multi-Head Attention-Based Autoencoder for Eliminating Electrode Motion Noise in ECG Applications.

Sensors (Basel, Switzerland)·2025

This study classifies neonatal cries for pain, hunger, or sleepiness using deep learning and machine learning. A hybrid approach achieved 88.89% accuracy in identifying infant distress signals.

Area of Science:

  • Medical Informatics
  • Signal Processing
  • Artificial Intelligence

Background:

  • Neonatal infant communication relies on distinct cry patterns signaling different needs.
  • Traditional audio signal analysis for infant cries is complex, requiring expert feature extraction.
  • Deep learning offers automatic feature extraction but typically needs large datasets.

Purpose of the Study:

  • To develop an accurate system for classifying neonatal cries into pain, hunger, and sleepiness categories.
  • To combine deep learning and machine learning to overcome data limitations in infant cry analysis.
  • To evaluate the effectiveness of a hybrid deep convolutional neural network (DCNN) and support vector machine (SVM) approach.

Main Methods:

  • Neonatal cry audio signals were converted into spectrogram images using the short-time Fourier transform (STFT).
Keywords:
convolutional neural networkinfant cry classificationshort time fourier transformspectrogramsupport vector machine

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.2K

Related Experiment Videos

Last Updated: Oct 31, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.8K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.2K
  • Spectrogram images were processed by a deep convolutional neural network (DCNN) for feature extraction.
  • Extracted features were classified using a support vector machine (SVM) with different kernel functions (RBF, linear, polynomial).

    • Main Results:

    • The hybrid DCNN-SVM model demonstrated promising results in classifying neonatal cries.
    • The support vector machine with the radial basis function (SVM-RBF) kernel achieved the highest accuracy.
    • The kernel-based infant cry classification system reached an accuracy of 88.89%.

    Conclusions:

    • A combined DCNN feature extraction and SVM classification approach effectively analyzes neonatal cries, even with moderate data.
    • The SVM-RBF kernel provides superior performance for classifying infant cries based on spectrograms.
    • This hybrid method offers a robust solution for understanding neonatal communication through cries.