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: Jul 13, 2026

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem
10:15

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Published on: February 3, 2021

A Multi-Modal Expert-Driven ISAC Framework with Hierarchical Federated Learning for 6G Network.

Behzod Mukhiddinov1, Di He2, Wenxian Yu2

  • 1School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai 200240, China.

Sensors (Basel, Switzerland)
|February 27, 2026
PubMed
Summary

Related Concept Videos

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

441
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
441

You might also read

Related Articles

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

Sort by
Same author

Fractal-domain Vision Graph Neural Network for Remote Sensing Ground Target Classification.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Evaluation and management of DMD gene copy number variations detected by prenatal SNP-array testing.

BMC medical genomics·2026
Same author

Geometric Unscented Particle Filters on Lie Groups for State Estimation.

IEEE transactions on cybernetics·2026
Same author

Melatonin Prevents the Progression of MASLD via Inhibiting FFAs-Induced Ferroptosis through KEAP1/NRF2/HO-1 Pathway.

Biomolecules & therapeutics·2025
Same author

Prenatal Characterization of Houge-Janssens Syndrome Type 2: A Case Report and Systematic Review of Fetal Phenotypes Associated With PPP2R1A Mutations.

Molecular genetics & genomic medicine·2025
Same author

Therapeutic Drug Monitoring: A New Hope for Individualised Treatment with Venetoclax.

Current drug targets·2025

This study introduces an Expert-Driven Conditional Auxiliary Classifier Generative Adversarial Network (AC-GAN) for edge AI. The novel framework enhances federated learning on heterogeneous data, improving precision and privacy on resource-constrained devices.

Area of Science:

  • Artificial Intelligence
  • Edge Computing
  • Machine Learning

Background:

  • Federated learning on edge devices faces challenges with non-IID data, model heterogeneity, and resource constraints.
  • Existing methods often assume idealized data distributions or require centralized data, limiting practical applicability.
  • Privacy preservation and communication efficiency are critical for real-world edge AI deployments.

Purpose of the Study:

  • To propose a novel Expert-Driven Conditional Auxiliary Classifier Generative Adversarial Network (AC-GAN) framework for heterogeneous multi-modal federated learning at the edge.
  • To address statistical non-IID data, model heterogeneity, privacy protection, and resource constraints in edge AI.
  • To enhance global model generalization and privacy preservation without sharing raw data.

Main Methods:

Keywords:
6GISACexpert modelshierarchical federated learningmulti-modal data fusion

Related Experiment Videos

Last Updated: Jul 13, 2026

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem
10:15

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Published on: February 3, 2021

  • Developed a collaborative synthesis and aggregation mechanism guided by local experts for conditional data generation.
  • Implemented hierarchical model updates between client and server levels to mitigate bias and reduce communication overhead.
  • Utilized an Expert-Driven Conditional Auxiliary Classifier Generative Adversarial Network (AC-GAN) for realistic data augmentation on edge nodes.

Main Results:

  • The proposed AC-GAN framework achieved substantially improved precision and false positive trade-offs (e.g., precision 0.89) compared to federated baselines.
  • Demonstrated consistent outperformance in accuracy, convergence stability, and privacy preservation across synthetic and real datasets.
  • Validated the framework's robustness in practical multi-modal settings on edge AI devices like the NVIDIA Jetson Orin Nano.

Conclusions:

  • Expert-guided conditional generative modeling is a promising direction for scalable, privacy-aware edge intelligence.
  • The AC-GAN framework effectively handles statistical non-IID data and model heterogeneity in federated learning.
  • The approach offers a viable solution for enhancing edge AI capabilities under real-world constraints.