Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

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

Summary

This summary is machine-generated.

Related Concept Videos

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

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...

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

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

Same author

Establishing reference values for age-related fecal calprotectin in healthy children aged 0-4 years: a systematic review and meta-analysis.

PeerJ·2025

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

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:

6G ISAC expert models hierarchical federated learning multi-modal data fusion

Related Experiment Videos

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.