EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Intelligent and secure Federated Learning for data elements circulation in heterogeneous edge computation

Geng Cheng, Jianbo Liu

ICST Transactions on Scalable Information Systems · 28.07.2026 · 13 (1)

DOI: 10.4108/eetsis.14118 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICST Transactions on Scalable Information Systems, online erschienen am 28.07.2026. Verfasst von Geng Cheng und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION: Heterogeneous edge computing creates data islands due to privacy and environmental heterogeneity. Current solutions lack an overall approach. OBJECTIVES: This study constructs a federated learning framework for secure data element circulation, mitigating low-power node tailing, balancing communication with accuracy, and adapting to non-IID data, advancing intelligent systems and cybersecurity. METHODS: The framework fuses Dynamic Clustering, Adaptive Gradient Transmission, and Data Distribution Alignment. Validation uses simulations against existing technologies. RESULTS: The proposed method achieves 0.892±0.021 comprehensive performance, 11.1%–13.6% higher than existing technologies. Under 20% network interruption, attenuation is 3.3% vs. 8.6%–12.5%. Data flow reaches 18.6±0.7 MB/s; privacy leakage is 0.8±0.2 bit. CONCLUSION: This study provides reliable support for safe, efficient data element circulation, advancing intelligent systems and cybersecurity.

Zitieren

APA

Cheng, G., & Liu, J. (2026). Intelligent and secure Federated Learning for data elements circulation in heterogeneous edge computation. ICST Transactions on Scalable Information Systems, 13(1). https://doi.org/10.4108/eetsis.14118

Vancouver

Cheng G, Liu J. Intelligent and secure Federated Learning for data elements circulation in heterogeneous edge computation. ICST Transactions on Scalable Information Systems. 2026;13(1). doi:10.4108/eetsis.14118

BibTeX
@article{Cheng2026,
  author = {Cheng, Geng and Liu, Jianbo},
  title = {Intelligent and secure Federated Learning for data elements circulation in heterogeneous edge computation},
  journal = {ICST Transactions on Scalable Information Systems},
  year = {2026},
  volume = {13},
  number = {1},
  doi = {10.4108/eetsis.14118}
}
Kostenlos starten →