Special Issues
Table of Content

Advances in AI Techniques in Convergence ICT

Submission Deadline: 30 June 2025 (closed) View: 2094 Submit to Journal

Guest Editors

Dr. Ji Su Park

Email: jisupark@jj.ac.kr

Affiliation: Department of Computer Science Engineering, Jeonju University, Jeonju, 55069, Republic of Korea

Homepage:

Research Interests: IIoT, Cloud Computing, Mobile computing

图片3.png

 

Dr. Yan Li

Email: leeyeon@inha.ac.kr

Affiliation: Department of Electrical and Computer Engineering, Inha University, Incheon, 22212, Republic of Korea

Homepage:

Research Interests: Deep Learning, Database, IoT, Computer Vision

图片4.png


Summary

The recent advancements in smart devices, mobile networks, and computing technologies are ushering us into a new era of Convergence ICT. To enable these smart devices to provide intelligent services, machine learning techniques are essential for training powerful predictive models. A common approach involves collecting distributed user data to a central cloud for deep learning model training. However, transferring massive amounts of data to the cloud center can cause significant transmission pressure on the backbone network. Additionally, increasing concerns about data privacy and the enforcement of privacy protection laws make it impractical to transmit data from end devices to the cloud.


Despite these advancements, existing AI techniques face several limitations that require novel solutions to better comprehend and improve their potential for decision-making in various real-world applications. Key challenges for employing diverse AI techniques include network management, communication efficiency, client selection and scheduling, resource management, security and privacy concerns, incentive mechanisms, and service management and pricing. Addressing these challenges calls for various techniques, including but not limited to: 

· Data augmentation

· Active learning

· Multi-task learning

· Knowledge distillation

· Model compression

· Game theory

· Trust and reputation systems

· Multi-objective optimization

· Reinforcement learning

· AI based algorithm/method in Convergence ICT 

· Privacy and Security in Convergence ICT 

· Data Analysis in Convergence ICT


Keywords

Convergence ICT, AI Techniques, Security, Data Analysis

Published Papers


  • Open Access

    ARTICLE

    FedCW: Client Selection with Adaptive Weight in Heterogeneous Federated Learning

    Haotian Wu, Jiaming Pei, Jinhai Li
    CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-20, 2026, DOI:10.32604/cmc.2025.069873
    (This article belongs to the Special Issue: Advances in AI Techniques in Convergence ICT)
    Abstract With the increasing complexity of vehicular networks and the proliferation of connected vehicles, Federated Learning (FL) has emerged as a critical framework for decentralized model training while preserving data privacy. However, efficient client selection and adaptive weight allocation in heterogeneous and non-IID environments remain challenging. To address these issues, we propose Federated Learning with Client Selection and Adaptive Weighting (FedCW), a novel algorithm that leverages adaptive client selection and dynamic weight allocation for optimizing model convergence in real-time vehicular networks. FedCW selects clients based on their Euclidean distance from the global model and dynamically adjusts More >

  • Open Access

    REVIEW

    Federated Learning in Convergence ICT: A Systematic Review on Recent Advancements, Challenges, and Future Directions

    Imran Ahmed, Misbah Ahmad, Gwanggil Jeon
    CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 4237-4273, 2025, DOI:10.32604/cmc.2025.068319
    (This article belongs to the Special Issue: Advances in AI Techniques in Convergence ICT)
    Abstract The rapid convergence of Information and Communication Technologies (ICT), driven by advancements in 5G/6G networks, cloud computing, Artificial Intelligence (AI), and the Internet of Things (IoT), is reshaping modern digital ecosystems. As massive, distributed data streams are generated across edge devices and network layers, there is a growing need for intelligent, privacy-preserving AI solutions that can operate efficiently at the network edge. Federated Learning (FL) enables decentralized model training without transferring sensitive data, addressing key challenges around privacy, bandwidth, and latency. Despite its benefits in enhancing efficiency, real-time analytics, and regulatory compliance, FL adoption faces… More >

  • Open Access

    ARTICLE

    Integration of Federated Learning and Graph Convolutional Networks for Movie Recommendation Systems

    Sony Peng, Sophort Siet, Ilkhomjon Sadriddinov, Dae-Young Kim, Kyuwon Park, Doo-Soon Park
    CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2041-2057, 2025, DOI:10.32604/cmc.2025.061166
    (This article belongs to the Special Issue: Advances in AI Techniques in Convergence ICT)
    Abstract Recommendation systems (RSs) are crucial in personalizing user experiences in digital environments by suggesting relevant content or items. Collaborative filtering (CF) is a widely used personalization technique that leverages user-item interactions to generate recommendations. However, it struggles with challenges like the cold-start problem, scalability issues, and data sparsity. To address these limitations, we develop a Graph Convolutional Networks (GCNs) model that captures the complex network of interactions between users and items, identifying subtle patterns that traditional methods may overlook. We integrate this GCNs model into a federated learning (FL) framework, enabling the model to learn… More >

  • Open Access

    ARTICLE

    Smart Contract Vulnerability Detection Using Large Language Models and Graph Structural Analysis

    Ra-Yeon Choi, Yeji Song, Minsoo Jang, Taekyung Kim, Jinhyun Ahn, Dong-Hyuk Im
    CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 785-801, 2025, DOI:10.32604/cmc.2025.061185
    (This article belongs to the Special Issue: Advances in AI Techniques in Convergence ICT)
    Abstract Smart contracts are self-executing programs on blockchains that manage complex business logic with transparency and integrity. However, their immutability after deployment makes programming errors particularly critical, as such errors can be exploited to compromise blockchain security. Existing vulnerability detection methods often rely on fixed rules or target specific vulnerabilities, limiting their scalability and adaptability to diverse smart contract scenarios. Furthermore, natural language processing approaches for source code analysis frequently fail to capture program flow, which is essential for identifying structural vulnerabilities. To address these limitations, we propose a novel model that integrates textual and structural… More >

Share Link