Density-Clustering Aggregation for Personalized Federated Learning With AI-Enabled Aerial and Edge Computing in UAVs

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12310%2F25%3A43910508" target="_blank" >RIV/60076658:12310/25:43910508 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10834535" target="_blank" >https://ieeexplore.ieee.org/document/10834535</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/JIOT.2024.3522164" target="_blank" >10.1109/JIOT.2024.3522164</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Density-Clustering Aggregation for Personalized Federated Learning With AI-Enabled Aerial and Edge Computing in UAVs

Popis výsledku v původním jazyce

This research introduces the density-clustering-based aggregation for personalized federated learning (DCPFL) algorithm, which utilizes DBSCAN clustering to enhance model accuracy in AI-enabled aerial and edge computing contexts, particularly for uncrewed aerial vehicles (UAVs). The DCPFL framework promotes model sharing among clients, fostering the development of personalized and optimized models. DBSCAN is beneficial in automatically determining cluster numbers using EPS neighborhoods and MinPts, with parameter optimization achieved through cross-experimental analysis. We further refined the model exchange mechanism by integrating a moving average prediction model to optimize the timing of these exchanges. Tests conducted on three public datasets covering two different machine learning (ML) tasks show that DCPFL surpasses existing methods, offering greater accuracy and enhanced adaptability in varied data environments. Implementing this algorithm in UAV networks leverages AI capabilities in aerial and edge computing to efficiently balance personalized modeling requirements with high performance, showcasing its potential to push federated learning (FL) forward in complex and dynamic settings.

Název v anglickém jazyce

Density-Clustering Aggregation for Personalized Federated Learning With AI-Enabled Aerial and Edge Computing in UAVs

Popis výsledku anglicky

This research introduces the density-clustering-based aggregation for personalized federated learning (DCPFL) algorithm, which utilizes DBSCAN clustering to enhance model accuracy in AI-enabled aerial and edge computing contexts, particularly for uncrewed aerial vehicles (UAVs). The DCPFL framework promotes model sharing among clients, fostering the development of personalized and optimized models. DBSCAN is beneficial in automatically determining cluster numbers using EPS neighborhoods and MinPts, with parameter optimization achieved through cross-experimental analysis. We further refined the model exchange mechanism by integrating a moving average prediction model to optimize the timing of these exchanges. Tests conducted on three public datasets covering two different machine learning (ML) tasks show that DCPFL surpasses existing methods, offering greater accuracy and enhanced adaptability in varied data environments. Implementing this algorithm in UAV networks leverages AI capabilities in aerial and edge computing to efficiently balance personalized modeling requirements with high performance, showcasing its potential to push federated learning (FL) forward in complex and dynamic settings.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE INTERNET OF THINGS JOURNAL

ISSN

2327-4662

e-ISSN

2327-4662

Svazek periodika

12

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

11220-11232

Kód UT WoS článku

001477382800018

EID výsledku v databázi Scopus

2-s2.0-105003876018