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

You might also read

Related Articles

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

Sort by
Same author

Tuning Deep Learning for Predicting Aluminum Prices Under Different Sampling: Bayesian Optimization Versus Random Search.

Entropy (Basel, Switzerland)·2026
Same author

Energy Measures as Biomarkers of SARS-CoV-2 Variants and Receptors.

Bioengineering (Basel, Switzerland)·2026
Same author

A Deep Learning-Based Ensemble System for Brent and WTI Crude Oil Price Analysis and Prediction.

Entropy (Basel, Switzerland)·2025
Same author

An Effective and Fast Model for Characterization of Cardiac Arrhythmia and Congestive Heart Failure.

Diagnostics (Basel, Switzerland)·2025
Same author

Fractals in Neuroimaging.

Advances in neurobiology·2024
Same author

Infant Cry Signal Diagnostic System Using Deep Learning and Fused Features.

Diagnostics (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jan 10, 2026

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

11.4K

Distinguishing Between Healthy and Unhealthy Newborns Based on Acoustic Features and Deep Learning Neural Networks

Salim Lahmiri1,2, Chakib Tadj2, Christian Gargour2

  • 1Department of Supply Chain and Business Technology Management, John Molson School of Business, Concordia University, Montreal, QC H3G 1M8, Canada.

Entropy (Basel, Switzerland)
|November 26, 2025
PubMed
Summary

Deep feedforward neural networks (DFFNN) accurately classify newborn health using cry acoustics. Optimized DFFNN models achieved high accuracy, outperforming previous methods for infant health assessment.

Keywords:
Bayesian optimizationMel-frequency cepstral coefficientsauditory-inspired amplitude modulationdeep feedforward neural networksnewborn cryprosodyrandom search optimization

More Related Videos

Infant Auditory Processing and Event-related Brain Oscillations
06:34

Infant Auditory Processing and Event-related Brain Oscillations

Published on: July 1, 2015

16.9K
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

7.2K

Related Experiment Videos

Last Updated: Jan 10, 2026

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

11.4K
Infant Auditory Processing and Event-related Brain Oscillations
06:34

Infant Auditory Processing and Event-related Brain Oscillations

Published on: July 1, 2015

16.9K
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

7.2K

Area of Science:

  • Biomedical Engineering
  • Computational Linguistics
  • Neonatal Medicine

Background:

  • Voice analysis is increasingly used to aid clinical decision-making.
  • Distinguishing healthy from unhealthy newborns is crucial for early intervention.

Purpose of the Study:

  • To develop and evaluate deep feedforward neural networks (DFFNN) for classifying newborn health status.
  • To compare the performance of DFFNN optimized with Bayesian optimization (BO) and random search (RS).

Main Methods:

  • Trained DFFNN models using acoustic features from newborn cries: auditory-inspired amplitude modulation (AAM), Mel Frequency Cepstral Coefficients (MFCC), and prosody.
  • Optimized DFFNN configurations using Bayesian optimization (BO) and random search (RS) algorithms.
  • Evaluated model performance using a ten-fold cross-validation protocol.

Main Results:

  • DFFNN achieved the highest classification rate when trained with all acoustic features.
  • DFFNN-BO reached 87.80% ± 0.23 accuracy, and DFFNN-RS reached 86.12% ± 0.33 accuracy.
  • Both optimized DFFNN models surpassed existing methods on the same dataset.

Conclusions:

  • Deep feedforward neural networks are effective for classifying newborn health based on cry acoustics.
  • Optimized DFFNN models demonstrate superior performance compared to prior approaches.
  • This technology holds promise for improving neonatal diagnostic capabilities.