[AISWorld] cfp Special Issue "Federated Learning for Blockchain Assisted IoT Systems: Architecture, Algorithms, And Applications", Connection Science

[Editorial Manager]

[Apologies if multiple copies of this email are received]

Special issue: Federated Learning for Blockchain Assisted IoT Systems: Architecture, Algorithms, And Applications
Connection Science, Taylor & Francis
https://tinyurl.com/2waw8pe8
CiteScore: 3.4 (2021)


The FL system for blockchain assisted IoT systems to work in two important phases. In the first phase, the raw model provided by the manufacturers undergoes training based on the data collected in the user's environment. In certain situations, the data can be collected through pervasive devices such as smartphones, laptops etc., and processed through mobile edge computing services. These data models are then authorized by the users and sent to the blockchain systems. The centralized aggregator in the FL systems is replaced by the blockchain system in order to eliminate malicious or tampered data. In the second phase, an average of the received data models is calculated or mined. In the whole process, the user's organization will act as a mining system hence helping in crowdsourcing. Research findings also suggest a normalization technique to further secure the privacy of user data. The applications of FL have extended to a great extent in the Industrial Internet of Things (IIoT) since it has an emergency privacy protection ML algorithm. Nevertheless, the efficacy of FL systems for blockchain-assisted IoT suffers from certain drawbacks such as difficulty in handling heterogeneous data, scalability etc. Research must be focused on improving the drawbacks and enhancing the overall performance and application range of such systems.

Original contributions are being sought in a wide range of related topics including, but not limited to, the following:
- Federated Learning (FL) for blockchain-powered edge intelligence for secure data transfer.
- Techniques to address the existing limitations in blockchain-based edge intelligence using federated learning systems.
- Framework for federated learning in blockchain-assisted Industrial Internet of Things (IIoT).
- Novel system architecture for healthcare database management using IoT and FL.
- Methods to overcome scalability issues in FL based IoT secured by blockchain technologies.
- Comparison of federated learning and classical distributed learning in terms of performance and efficiency for smart home systems.
- Innovative solutions for addressing system heterogeneity in pervasive mobile devices using FL and blockchain technologies.
- Federated optimization in blockchain-based heterogeneous smart and intelligent healthcare database networks.
- Development of an optimum resource allocation algorithm for FL in blockchain assisted IoT applications.
- Integration of asynchronous communication approach for federated learning in smart transportation systems.

Important Date
Manuscript deadline:  10 October 2022

Guest Editor(s)
Adhiyaman Manickam, Department of Computer Science University of Moncton, Canada
adhiyaman.m at ieee.org<mailto:adhiyaman.m at ieee.org>

J. Alfred Daniel, Dhanalakshmi Srinivasan Engineering College, Anna University, India.
alfreddaniel.j at ieee.org<mailto:alfreddaniel.j at ieee.org>

Dinesh Jackson Samuel, The University of Texas MD Anderson Cancer Center, Texas, United States
rsamuel at ieee.org<mailto:rsamuel at ieee.org>


Inquiries: for any questions about this Special issue, please contact the guest editors.