EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Federated parameter-free DBSCAN clustering and its application in image recognition

Fang Cheng, Zilong Deng iD, Mustafa Muwafak Alobaedy, Xiaocun Huang

PLOS One · 04.08.2026 · 21 (8) · e0355161

DOI: 10.1371/journal.pone.0355161 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.08.2026. Verfasst von Fang Cheng und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Technology, Anqing Vocational and Technical College, Anqing, China. Hauptthemen laut MEDLINE: Algorithms, Image Processing, Computer-Assisted, Pattern Recognition, Automated. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Natural Science Research Projects of Higher Education Institutions in Anhui Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

DBSCAN (A Density-Based Algorithm for Discovering Clusters in Spatial Databases with Noise) is a classic clustering algorithm. However, clustering distributed data with privacy protection in edge computing environments is a key challenge for DBSCAN. In this research, we combine federated clustering and DBSCAN and propose two secure federated parameter-free DBSCAN clustering methods, called FDBSCAN and FDBSCAN++. The process involves the following steps: (1) differential privacy is applied to the client data and adaptive DBSCAN is used at each client to identify core points; (2) the clients send the extracted core points to the server, where the server aggregates these to obtain the final global cluster centers (FDBSCAN and FDBSCAN++ use different methods in this step); (3) the final clusters are generated using these global centers. To verify the effectiveness of the proposed two algorithms, we use eight real datasets, including the large-scale image dataset MNIST. Compared with traditional and state-of-the-art (SOTA) improved DBSCAN and federated clustering algorithms, the proposed algorithms achieve better clustering accuracy. In addition, we also apply FDBSCAN++ to image clustering and segmentation tasks, which achieves satisfactory results.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsImage Processing, Computer-AssistedPattern Recognition, AutomatedClustering AlgorithmsCluster AnalysisFederated LearningHumans

Autor:innen und Institutionen

  • College of Information Technology, Anqing Vocational and Technical College, Anqing, China.
  • Faculty of Information Technology, City University Malaysia, Petaling Jaya, Malaysia.
  • Cangzhou Normal University, Cangzhou, China.

ORCID-Profile: Zilong Deng

Förderung

  • Key Natural Science Research Projects of Higher Education Institutions in Anhui Province

Zitieren

APA

Cheng, F., Deng, Z., Alobaedy, M. M., & Huang, X. (2026). Federated parameter-free DBSCAN clustering and its application in image recognition. PLOS One, 21(8), e0355161. https://doi.org/10.1371/journal.pone.0355161

Vancouver

Cheng F, Deng Z, Alobaedy MM, Huang X. Federated parameter-free DBSCAN clustering and its application in image recognition. PLOS One. 2026;21(8):e0355161. doi:10.1371/journal.pone.0355161

BibTeX
@article{Cheng2026,
  author = {Cheng, Fang and Deng, Zilong and Alobaedy, Mustafa Muwafak and Huang, Xiaocun},
  title = {Federated parameter-free DBSCAN clustering and its application in image recognition},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {8},
  pages = {e0355161},
  doi = {10.1371/journal.pone.0355161}
}
Kostenlos starten →