Skip to main navigation Skip to search Skip to main content

Detecting personal protective equipment (PPE) utilising YOLOv8 in a federated learning environment

  • Ioannis Makris
  • , Anastasios Lytos
  • , Konstantinos Kyranou
  • , Vasileios Argyriou
  • , Thomas Lagkas
  • , Konstantinos Filippos Kollias
  • , George F. Fragoulis
  • , Panagiotis Sarigianndis
  • University of Western Macedonia
  • Sidroco Holdings Ltd
  • International Hellenic University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In the construction industry, where worker safety is a paramount concern, the effective use of PPE is crucial. This study delves into an innovative approach by exploring the integration of Federated Learning (FL) with the YOLOv8 architecture for enhanced PPE object detection. A specialized construction safety dataset was utilized to conduct the corresponding experiments, comparing FL against conventional local training methodologies. The results have clearly shown the superiority of FL in terms of accuracy improvement of PPE object detection which opens a lot of paths for creative solutions leading to the progress of safety performance at construction sites, at the same time, while observing the strictest privacy and security issues for personal data that is a primary consideration in our data-driven era. The proposed solution achieved an average mAP of 79.52%, and an average Recall of 78.49%, proving its effectiveness over the centralized training.
Original languageEnglish
Title of host publicationETLTC2024 international conference series on ICT
Subtitle of host publicationentertainment technologies, and intelligent information management in education and industry
PublisherAIP Publishing
Volume3220
DOIs
Publication statusPublished - Jan 2024
EventThe 6th ETLTC International Conference on ICT Integration in Technical Education - Aizuwakamatsu, Japan
Duration: 23 Jan 202426 Jan 2024

Publication series

NameAIP Conference Proceedings (2024)
PublisherAIP Publishing
Number1
Volume3220
ISSN (Print)0094-243X

Conference

ConferenceThe 6th ETLTC International Conference on ICT Integration in Technical Education
Period23/01/2426/01/24

Keywords

  • Computer science and informatics

Fingerprint

Dive into the research topics of 'Detecting personal protective equipment (PPE) utilising YOLOv8 in a federated learning environment'. Together they form a unique fingerprint.

Cite this