International Journal of Web and Grid Services (9 papers in press)

Regular Issues

• Open Access

  A Novel Simplified Swarm Optimization of Convolutional Neural Network Weights ( Free Full-text Access )

  by Zhenyao Liu, Po-Hung Chiang, Chia-Ling Huang, Wei-Chang Yeh 
  Abstract: Convolutional Neural Network (CNN) is a feedforward neural network with multiple hidden layers using a neural network as the basic framework. CNN has the advantages of local neuron linkage and weight sharing and doesnt learn the same features under different filter processing, which improves computational efficiency and accuracy when avoiding over-fitting. In this study, we propose an algorithm based on Simplified Swarm Optimization (SSO), namely, SSO-CNN, as a solution to efficiently optimize the weights of one of the first released CNN models: LeNet. This method we developed using the advantages of SSO which is good at solving continuous problems. So that the accuracy of CNN can be improved stably in different test datasets. The results of experiments involving the MNIST, EMNIST, CIFAR-10, and SVHN datasets showed that the proposed algorithm was more efficient than traditional methods and it could be used with more complicated models like AlexNet, VGG, etc.
  Keywords: Convolutional Neural Network; Simplified Swarm Optimization; Machine Learning; Image Recognition; Weight Optimization.
  DOI: 10.1504/IJWGS.2026.10080880
   
  

• Open Access

  Repurchase Prediction Modelling of Retail Customer Behaviour: an AI-Driven Approach ( Free Full-text Access )

  by Yu Yu Yen, Jui Hung Kao, Horng-Twu Liaw, Guang Lei Lu, Jui-Ying Chen 
  Abstract: This study investigates how artificial intelligencedriven analytics can be leveraged to predict repurchase behavior and enhance customer value management in automotive department store chains. Using an automotive retailer as an empirical case, transaction data from a POS system are analyzed through the RFM (Recency, Frequency, Monetary) model to segment customers by value. The results demonstrate that RFM-based segmentation effectively identifies heterogeneous customer groups with distinct repurchase intentions and purchasing patterns. Building on this segmentation, AI-enabled predictive modeling provides actionable insights for anticipating customer behavior, supporting personalized marketing strategies, and optimizing product and service portfolios. The findings underscore the importance of implementing differentiated retention strategies and utilizing data-driven decision support in competitive retail environments. By integrating customer analytics with AI-based prediction, this study offers both theoretical contributions and practical guidance for retailers seeking to strengthen customer loyalty and achieve sustainable profitability.
  Keywords: automotive industry; crm; rfm model; marketing strategy.
  DOI: 10.1504/IJWGS.2026.10081324
   
  

• Open Access

  The ADDIE Instructional Design Model combined with AI Technology in the Design of an Auxiliary Correction System for IP-Oriented Template-based Assignment ( Free Full-text Access )

  by Yung-Hui Chen, Lawrence Y. Deng, Chun-Hsiung Tseng, Jian-Yu Chen, Xiang-Yann Lim 
  Abstract: This study develops an Auxiliary Correction System (ACS) for IP-Oriented Template-based Assignments (IPOTA) in a vocational university network laboratory course. The instructional design of the course and the system implementation were guided by the ADDIE model to reduce grading workload while improving feedback timeliness and student learning support. Each assignment embeds the students seat number into the IP configuration so that every submission is unique, reducing the risk of copying but increasing grading complexity. To address this problem, the ACS combines rule-based text normalisation, an answer database, and image-based text extraction using deep-learning methods to assist grading. In the reported implementation, the ACS reduced the average grading time to about 20 seconds per assignment and achieved 100% accuracy on the training set for the image-recognition task. The results indicate that the proposed approach can substantially reduce manual marking effort and provide a basis for earlier instructional intervention and learning analytics.
  Keywords: ADDIE Instructional Design Model; Artificial Intelligence (AI); Auxiliary Correction System (ACS); IP-Oriented Template-based Assignment (IPOTA); Prediction Models.
  DOI: 10.1504/IJWGS.2026.10081396
   
  
• Sensitive, critical and real-time application deployed as a web service in a multi-cloud architecture  
  by Rihem Zorgati, Hassen Hamdi, Khalil Ahmad Alsulbi 
  Abstract: Healthcare, financial, and online educational applications with real-time and sensitivity demands require low latency, high availability, and elastic infrastructure. Traditional single-cloud strategies often cannot provide these reliability and performance levels. We present in this paper a cloud broker (CB)-based multi-cloud system that dynamically allocates workloads among multiple vendors such as AWS, Azure, and GCP based on performance. Unlike conventional multi-cloud deployments, our approach utilises adaptive deployment strategies to minimise response times and enhance fault tolerance. Experimental findings suggest that the CB model reduces latency by up to 93% in mission-critical situations such as authentication, medical diagnosis, and financial transactions. This design offers a practical, scalable, and fault-tolerant framework for mission-critical real-time applications with an emphasis on trade-offs in operational complexity and cost-performance.
  Keywords: sensitive; critical; real-time application; web service; distributed computing; multi-cloud; cloud broker; internet of things; IoT.
  DOI: 10.1504/IJWGS.2026.10079887
   
  
• AI-enhanced reputation framework for avatars: combining GPT-3.5 and blockchain voting  
  by Duaa Alawfi, Hani Althubaiti, Farookh Khadeer Hussain 
  Abstract: The metaverse is a rapidly evolving digital environment where virtual entities interact and communicate. Establishing a robust framework for assessing avatar reputation is essential for maintaining trust and accountability in this decentralised space. To address this challenge, we propose AvatarRM, a framework for objective reputation computation in the metaverse. Leveraging GPT-3.5 Turbo, our approach dynamically identifies and refines reputation criteria through AI-driven analysis, ensuring adaptability to evolving metaverse dynamics. In addition, we integrate a smart contract-based voting mechanism, enabling decentralised community participation in reputation evaluation. This hybrid AI-blockchain system not only enhances the accuracy and relevance of reputation assessments but also fosters transparency and sustainability. Our study demonstrates how AI-generated criteria, combined with blockchain-powered voting, can create a flexible and reliable reputation framework tailored to the unique demands of virtual environments.
  Keywords: reputation criteria; avatar; metaverse.
  DOI: 10.1504/IJWGS.2026.10081201
   
  
• Blockchain for managing carbon credits: a systematic literature review  
  by Inam Alanazi, Firas Al-Doghman 
  Abstract: The increasing concern over climate change and its environmental impacts has led to a growing interest in carbon emissions reduction and sustainable practices. As governments, organisations, and individuals seek ways to mitigate their carbon footprint, the concept of carbon credits has gained prominence. Carbon credits provide a mechanism for incentivising carbon emissions reduction efforts by enabling the trading of emissions allowances. However, traditional carbon credit management systems often lack transparency, efficiency, and accuracy. Blockchain technology is a promising solution to solve these issues in many domains. Hence, we propose an intelligent blockchain for managing carbon credits (IBMCC) framework to solve these challenges. The IBMCC leverages blockchain technology to create a web-based, decentralised and transparent platform for carbon credit management, enabling secure and traceable transactions. Additionally, integrating intelligent technologies, such as smart contracts and machine learning algorithms, enhances the accuracy of carbon credit verification and allocation accuracy. This paper systematically reviews the existing literature to identify the research gaps at the intersection of carbon credits management and blockchain technology. It also presents the architecture and design of the IBMCC system, highlighting its essential components and functionalities.
  Keywords: blockchain; carbon credits; carbon trading; carbon pricing; double counting; carbon marketplace.
  DOI: 10.1504/IJWGS.2026.10080890
   
  
• Enhancing interoperability of ubiquitous devices through WS-CDL-based coordination  
  by Oscar A. Testa, Efraín R. Fonseca Carrera, Germán Montejano, Óscar Dieste 
  Abstract: The rapid proliferation of ubiquitous devices has transformed daily human interaction, creating a critical need for seamless communication between heterogeneous systems and users. Despite this evolution, true interoperability remains a significant challenge, largely hindered by proprietary protocols and a lack of standardised integration mechanisms. While web services have achieved maturity through robust composition standards, ubiquitous computing still lacks a unified framework, resulting in a notable gap between academic proposals and practical implementation. This research addresses these limitations by leveraging service-oriented architecture (SOA) principles to enhance device connectivity within pervasive ecosystems. Following a design science research methodology, we developed a coordination framework through iterative prototyping and evaluation. Our findings demonstrate that extending the web services choreography description language (WS-CDL) to meet the specific requirements of ubiquitous hardware significantly improves both integration and functional reach, offering a scalable and standardised alternative to current closed solutions.
  Keywords: ubiquitous devices; pervasive environments; service-oriented architecture; SOA; web services choreography description language; WS-CDL; framework.
  DOI: 10.1504/IJWGS.2026.10081222
   
  
• AI integrated spatial crowdsourcing for dependency-aware task: a web service perspective  
  by Naren Debnath, Sajal Mukhopadhyay, Leonard Barolli 
  Abstract: Dependency-aware task allocation remains relatively underexplored in spatial crowdsourcing (SC). Though a few works addressed this dependency-aware task allocation in SC, those works have not considered automatic dependent task segregation, efficient selection of task executers (TEs) through similarity grouping, and fair allocation of dependent tasks to the selected TEs. We propose a unified AI-integrated framework for dependency-aware task allocation in SC using topological sorting, locality sensitive hashing, multi-armed bandit, and coalitional game theoretic model. For scalable and modular implementation, we introduce a service oriented architecture where the information on dependent tasks, TEs, and other related information in SC is modelled as distributed web services accessible via application programming interfaces. Furthermore, our paper addresses the issue of procrastination. Simulation results demonstrate that the proposed framework significantly improves task allocation performance and fairness compared to baseline methods, while the proposed procrastination mitigation strategy achieves more balanced task distribution.
  Keywords: spatial crowdsourcing; dependency-aware task allocation; fairness; consistent hashing; task copies; task chains.
  DOI: 10.1504/IJWGS.2026.10081437
   
  

Special Issue on: Emerging Technology in Big Data, AI, and Green Learning Driving Towards Sustainable Web Service Development

• Optimality and Scalability of Semantic Web Service Composition with Hierarchical Parameter Relationship
  by Jung-Woon Yoo 
  Abstract: Semantic web service composition considers semantics for finding better solutions than syntactic web service composition. This paper focuses on hierarchical relationships among parameters of web services. A comprehensive mathematical model for semantic web service composition, into which hierarchical parameter relationships are incorporated, is presented as a general mathematical formulation. Experimental results demonstrate that the mathematical model for semantic composition finds hidden and better solutions that syntactic composition cannot find. The optimality of the solutions is empirically verified through extensive experiments. Furthermore, the scalability of the model is tested by comprehensive experiments to explore the impacts of eight key factors on web service composition. The mathematical model and the provided data sets are expected to serve as benchmarking tools for performance evaluation of heuristic algorithms for semantic web service composition. Finally, a web application is presented to visualize the semantic web service composition process, which is developed using the Django framework.
  Keywords: AI Planning; Web Service Composition; Semantics; Parameter Hierarchy; Mathematical Modeling.