Language selection

Government of Canada / Gouvernement du Canada

Search

SF2D: semi-supervised federated learning for fall detection using (un)labelled data in edge-cloud

From National Research Council Canada

Download
  1. (PDF, 10.7 MiB)
Linkhttps://caiac.pubpub.org/pub/elv97xmv/
AuthorSearch for: ; Search for: ; Search for: 1ORCID identifier: https://orcid.org/0000-0002-5406-2309; Search for: 1ORCID identifier: https://orcid.org/0000-0002-8470-3226; Search for: ; Search for: ; Search for: 1ORCID identifier: https://orcid.org/0000-0002-1342-6225; Search for:
Affiliation
  1. National Research Council of Canada. Digital Technologies
FormatText, Article
ConferenceCanadian Conference on Artificial Intelligence (Canadian AI 2025), May 26-29, 2025, Calgary, Alberta
Subjectsemi-supervised federated learning; fall detection; edge; cloud
Abstract
The aging population faces increased health risks, with falls being a major concern for individuals over 65, leading to healthcare strain and distress. We propose a semi-supervised federated learning-based fall detection (SF2D) method that leverages edge devices to maintain user privacy while ensuring accurate detection. Our approach first trains an unsupervised autoencoder with federated learning, then uses its encoder to train a cloud-based classifier with benchmark datasets. Our proposed SF2D improves accuracy by 1% and recall by 4% over state-of-the-art systems, offering a practical, accurate solution for fall detection and elderly care.
Publication date
PublisherCanadian Artificial Intelligence Association
Licence
In
  • Proceedings of the 38th Canadian Conference on Artificial Intelligence, 2025S146 (19 May 2025).
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier5142c906-e5f5-45ee-a070-1486125ce44a
Record created2025-07-10
Record modified2025-07-10
Date modified: