Return
Federated learning optimization: A computational blockchain process with offloading analysis to enhance security
DOI:10.1016/j.eij.2023.100406.png)
Abstract
En 中文
The Internet of Things (IoT) technology in various applications used in data processing systems requires high security because more data must be saved in cloud monitoring systems. Even though numerous procedures are in place to increase the security and dependability of data in IoT applications, the majority of outside users can decode any transferred data at any time. Therefore, it is essential to include data blocks that, under any circumstance, other external users cannot understand. The major significance of proposed method is to incorporate an offloading technique for data processing that is carried out by using block chain technique where complete security is assured for each data. Since a problem methodology is designed with respect to clusters a load balancing technique is incorporated with data weights where parametric evaluations are made in real time to determine the consistency of each data that is monitored with IoT. The examined outcomes with five scenarios process that projected model on offloading analysis with block chain proves to be more secured thereby increasing the accuracy of data processing for each IoT applications to 89%.
Keywords:
Internet of Things (IoT)
Blockchain
Data blocks
Federated learning
Security
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.3
Papers:
800
Citations:
1.4K
Organization
Cited Papers
Development of edge computing and classification using The Internet of Things with incremental learning for object detection
INTERNET OF THINGS
IF7.6
From Hype to Reality: Unveiling the Promises, Challenges and Opportunities of Blockchain in Supply Chain Systems
SUSTAINABILITY
IF3.3
A quantum trust and consultative transaction-based blockchain cybersecurity model for healthcare systems
SCIENTIFIC REPORTS
IF3.9

