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 Systems-I01:26

Classification of Systems-I

367
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
367

You might also read

Related Articles

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

Sort by
Same author

Systemic Inflammatory Markers and Intracranial Atherosclerosis: Road to Nowhere? A Meta-analysis.

Neuroepidemiology·2026
Same author

Radiomic Carotid Plaque Features Integrated into Machine Learning Models for Cardiovascular Risk Prediction.

Ultrasound in medicine & biology·2026
Same author

Impact of Attenuation Threshold Selection on the Quantification of Carotid Calcification on CTA.

AJNR. American journal of neuroradiology·2026
Same author

Integrating cardiac CT into the diagnostic pathway of Takotsubo syndrome: current evidence and future directions.

European journal of radiology·2026
Same author

Attention mechanisms in UNet variants for medical/non-medical image segmentation: A comprehensive and state-of-the-art narrative review.

Computers in biology and medicine·2026
Same author

Predictive modeling of drain current in advanced FET architectures using ML-based TCAD calibration.

Scientific reports·2026

Related Experiment Video

Updated: Oct 19, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.9K

Artificial intelligence-based hybrid deep learning models for image classification: The first narrative review.

Biswajit Jena1, Sanjay Saxena1, Gopal K Nayak1

  • 1Department of CSE, International Institute of Information Technology, Bhubaneswar, India.

Computers in Biology and Medicine
|September 18, 2021
PubMed
Summary
This summary is machine-generated.

Hybrid deep learning (HDL) models, fusing two or more deep learning architectures, offer superior performance in AI-driven image classification. This review provides the first comprehensive overview of HDL applications and their impact across various fields.

Keywords:
Artificial intelligenceDeep learningHybrid deep learningPerformanceRisk-of-biasSpatialSpatial-temporalTemporal

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Related Experiment Videos

Last Updated: Oct 19, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.9K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Artificial intelligence (AI) significantly impacts image classification, with deep learning (DL) enhancing automation and accuracy.
  • Solo deep learning (SDL) uses single architectures, while hybrid deep learning (HDL) fuses two or more DL architectures for improved capabilities.
  • HDL models are increasingly popular, yet a comprehensive review of their applications was previously unavailable.

Purpose of the Study:

  • To provide the first narrative review of hybrid deep learning (HDL) models in AI-based image classification.
  • To analyze the characteristics and applications of HDL models across diverse domains.
  • To categorize HDL approaches based on their evolution within computer vision.

Main Methods:

  • A PRISMA search strategy was utilized across major academic databases (Google Scholar, PubMed, IEEE, Elsevier Science Direct).
  • 127 relevant HDL studies were systematically reviewed and analyzed.
  • HDL models were categorized into spatial, temporal, and spatial-temporal based on computer vision evolution, with detailed attribute analysis.

Main Results:

  • Hybrid deep learning (HDL) models demonstrate stable and superior performance by integrating strengths from multiple DL or DL and ML models.
  • HDL applications are rapidly expanding in both medical and non-medical fields.
  • The risk of bias in DL and HDL models remains a significant and debatable concern.

Conclusions:

  • Hybrid deep learning (HDL) models represent an advanced approach to AI-powered image classification, offering enhanced performance.
  • The review highlights the growing adoption and diverse applications of HDL across various sectors.
  • Further investigation into the risks and biases associated with HDL models is warranted.