Call for Papers - AI and Federated Learning for Efficient Information Processing in Intelligent IoT Applications


Background of this SI:

The Internet of Things (IoT) has recently found applications in almost every industry, including industrial operations, healthcare, agriculture, smart city deployment, and data security systems. Furthermore, the IoT is being used in various industries, including military applications, patient monitoring in hospitals, cyber security systems, smart agriculture, self-driving vehicles, and logistics applications. The applications mentioned above use IoT due to its advantages in detecting and sending data received from the environment through wireless sensor networks. Apart from the above difficulties, IoT also confronts certain backlogs in data security, data transmission power, and data processing capabilities. Sensitive data acquired from IoT devices installed in various distant locations is analyzed using powerful machine learning and artificial intelligence techniques. Thus, specific processes inside AI that aid in limiting data leakage and ensuring security for sensitive data may be employed. The desired goal might be achieved using federated learning algorithms to analyses data acquired from sensitive environments such as the military and medical applications without causing data leakage.

Federated learning exacerbates the requirement for distributed data collected from various Internet of Things devices deployed in a scattered environment. The benefits of federated learning in information processing can improve hardware efficiency by obviating the need for sophisticated central processing servers. Moreover, data decentralization enables data acquisition for computing at local devices, obviating the requirement for a centralized server for computation and analysis.  In other words, the decentralization process enabled by federated learning results in high-speed data processing and a low probability of a single point of failure. Other federated learning applications in data analysis include model development for sensitive applications such as face identification, predictive analysis, data diversity, continuous learning, and voice recognition approaches.

With federated learning machine learning models, artificial intelligence might potentially improve data processing efficiency in an IoT network. Furthermore, artificial intelligence techniques such as deep learning models, neural networks, fuzzy data processing methods, object identification and analysis, and enhanced analytical technologies.  Along with the above AI technologies, the utilization of edge computing, blockchain, and quantum computing techniques may be leveraged to improve data safety and security.

This special issue sheds light on the current level of research offered on federated learning combined with AI approaches for analyzing data obtained from IoT. Thus, academics and industrialists may include a variety of cutting-edge technological applications and federated learning models into IoT data analysis. Furthermore, cyber security challenges relate to authentication, intrusion detection, spoofing attack prevention, multimedia forensics, and gender classifications.  

Topics of Interest:

  • An optimized approach to the on-device application of lightweight federated learning models for IoT
  • A novel framework deployment for achieving security of data collected from IoT networks
  • Deployment of open-source tools for secure federated learning in IoT
  • Implementation of federated learning for secure information processing along with deep learning for IoT
  • Distributed data processing for federated learning in edge and blockchain environments
  • Enhanced approach for federated learning models for computer vision and spatial applications deployed with IoT
  • Effective image/video forensics applied to multimedia applications with federated learning and deep neural networks
  • Protection against information leakage for IoT data with federated learning and neural network analysis
  • Data protection for the Industry 4.0 applications related to IoT data with federated learning and fuzzy methods
  • Application of pervasive computing along with federated learning for secure IoT data analysis


Manuscript submission deadline: December 15, 2022
Authors notification: March 10, 2023
Final notification: August 30, 2023

Guest Editors:
Raja Krishnamoorthi (Managing Guest Editor), CMR Engineering College, Telangana, Hyderabad, India
A. Shanthini, School of Computing, SRMIST, Kattankulathur, India
Bouziane Brik, Burgundy (Bourgogne) University, France