Blockchain-Integrated Edge-Cloud-Enabled Healthcare Data Analytics Based on Distributed Federated Learning and Deep Neural Networks
Mesopotamian Journal of CyberSecurity · 15.04.2026 · 5 (3) · 1122-1140
DOI: 10.58496//mjcs/2025/060 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mesopotamian Journal of CyberSecurity, online erschienen am 15.04.2026. Verfasst von Mazin Abed Mohammed und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The exponential growth of healthcare Internet of Things (IoT) data necessitates secure, low-latency analytics that extend beyond centralized architectures. This paper presents BDAFL DNN, a blockchain-integrated data analytics framework that combines Federated Learning (FL) and Deep Neural Networks (DNNs) for real-time, privacy-preserving healthcare analytics across edge and cloud resources. Local devices such as smartwatches and phones collect noninvasive time series sensor streams (heart rate, temperature, and abdomen sensors), perform on device DNN training, and send only model updates to healthcare edge nodes, where a blockchain ledger validates updates for integrity and traceability; validated updates are then aggregated in the cloud via FL to produce a global model without sharing raw data. In a simulation study against representative baselines, BDAFL DNN reduced execution time, energy use, and resource consumption, lowered the deadline miss ratio, and improved blockchain validation correctness. These results show that integrating blockchain with FL-driven edge and cloud DNN analytics can deliver scalable, secure, and timely insights for future healthcare IoT systems. Reason for Expression of Concern:The Editors wish to alert readers to potential concerns regarding the reliability of the findings reported in “Blockchain-Powered Dynamic Segmentation in Personal Health Record”. The journal has initiated an additional editorial assessment of the article’s methodology, data provenance, and reported outcomes to confirm their reliability and reproducibility. This notice is issued to ensure transparency while the review is ongoing. The Expression of Concern does not constitute a final determination regarding the validity of the work. The journal will update readers once the assessment is completed and will take any necessary editorial action in accordance with the journal’s policies and COPE guidance.See expression of concern available at:https://doi.org/10.58496/2026/017 https://mesopotamian.press/journals/index.php/CyberSecurity/article/view/1041
Zitieren
APA
Mohammed, M. A., Ghani, M. K. A., Al-Mashhadani, I. B., Memon, S., Lakhan, A., Marhoon, H. A., & Albahar, M. A. (2026). Blockchain-Integrated Edge-Cloud-Enabled Healthcare Data Analytics Based on Distributed Federated Learning and Deep Neural Networks. Mesopotamian Journal of CyberSecurity, 5(3), 1122-1140. https://doi.org/10.58496//mjcs/2025/060
Vancouver
Mohammed MA, Ghani MKA, Al-Mashhadani IB, Memon S, Lakhan A, Marhoon HA, et al. Blockchain-Integrated Edge-Cloud-Enabled Healthcare Data Analytics Based on Distributed Federated Learning and Deep Neural Networks. Mesopotamian Journal of CyberSecurity. 2026;5(3):1122-1140. doi:10.58496//mjcs/2025/060
BibTeX
@article{Mohammed2026,
author = {Mohammed, Mazin Abed and Ghani, Mohd Khanapi Abd and Al-Mashhadani, Israa Badr and Memon, Sajida and Lakhan, Abdullah and Marhoon, Haydar Abdulameer and Albahar, Marwan Ali},
title = {Blockchain-Integrated Edge-Cloud-Enabled Healthcare Data Analytics Based on Distributed Federated Learning and Deep Neural Networks},
journal = {Mesopotamian Journal of CyberSecurity},
year = {2026},
volume = {5},
number = {3},
pages = {1122--1140},
doi = {10.58496//mjcs/2025/060}
}
EUVIMED