Special Issues
Table of Content

AI-Driven Computational Networks and Cyber-Physical Systems: Models, Optimization, and Applications

Submission Deadline: 31 January 2027 View: 568 Submit to Special Issue

Guest Editor(s)

Dr. Aqeel Sahi

Email: aqeel.sahi@unisq.edu.au

Affiliation: School of Science,  Engineering and Digital Technologies, University of Southern Queensland, Queensland, Australia

Homepage:

Research Interests: artificial intelligence and machine learning for computational networks and cyber-physical systems, modeling, optimization, security, edge intelligence, and real-world applications in smart and autonomous systems


Assoc. Prof. Shahab Abdulla

Email: shahab.abdulla@unisq.edu.au

Affiliation: School of Business, Law, Humanities and Pathways, University of Southern Queensland,  Queensland, Australia

Homepage:

Research Interests: biomedical engineering, complex medical engineering, networked systems, intelligent control, computer control systems, robotics, artificial intelligence


Dr. Mohammed Diykh

Email: mohammed.diykh@unisq.edu.au

Affiliation: School of Business, Law, Humanities and Pathways, University of Southern Queensland, Queensland, Australia

Homepage:

Research Interests: artificial intelligence, applied computing not elsewhere classified, cybersecurity and privacy, applied computing


Dr. Muntadher Ali

Email: muntadher.ali@naps.edu.au

Affiliation: National Academy of Professional Studies, Sydney, Australia

Homepage:

Research Interests: UAV communication, resource allocation, and optimization


Summary

The rapid convergence of artificial intelligence (AI) with computational networks and cyber-physical systems (CPS) is transforming modern digital infrastructure, enabling intelligent, adaptive, and autonomous operations. This research area is critical for advancing smart systems across industries such as transportation, healthcare, energy, and communications.

This Special Issue aims to explore recent advances in AI-driven models, optimization techniques, and real-world applications in computational networks and cyber-physical systems. It focuses on integrating machine learning, deep learning, and intelligent algorithms with networked and physical environments to enhance performance, scalability, security, and reliability. The scope includes theoretical developments, system design, simulation, and practical implementations addressing challenges such as resource allocation, real-time decision-making, and system resilience. Contributions that bridge the gap between AI theory and deployment in next-generation smart and connected systems are particularly encouraged.

Suggested Themes:
· AI-enabled optimization in communication and computer networks
· Machine learning for cyber-physical system modeling and control
· Intelligent resource allocation and scheduling in distributed systems
· Security, privacy, and trust in AI-driven CPS and networks


Keywords

AI, CPS, computational networks, deep learning, machine learning, network optimization, intelligent systems, security and privacy

Published Papers


  • Open Access

    ARTICLE

    A MAML-Based Federated Meta-Learning Framework for Wireless Network Traffic Prediction

    Yuan Feng, Xiaotong Li, Xinhua Hu, Jianwei Zhang, Zengyu Cai, Liang Zhu
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2026.087978
    (This article belongs to the Special Issue: AI-Driven Computational Networks and Cyber-Physical Systems: Models, Optimization, and Applications)
    Abstract Wireless network traffic prediction enables operators to anticipate network trends, proactively develop network management strategies, and intelligently allocate network resources, thereby improving network service quality and enhancing users’ internet experience. Existing centralized network traffic prediction methods require transmitting large volumes of traffic data, which consumes significant network resources, incurs extra communication costs, and faces difficulties in full data sharing due to privacy concerns. Federated learning is a distributed learning method for multi-client joint training without sharing between clients, which can effectively solve such problems. However, the network traffic prediction method based on federated learning has… More >

Share Link