International Journal of Grid and Utility Computing (14 papers in press)

Regular Issues

• Recommendation system based on space-time user similarity
  by Wei Luo, Zhihao Peng, Ansheng Deng 
  Abstract: With the advent of 5G, the way people get information and the means of information transmission have become more and more important. As the main platform of information transmission, social media not only brings convenience to people's lives, but also generates huge amounts of redundant information because of the speed of information updating. In order to meet the personalised needs of users and enable users to find interesting information in a large volume of data, recommendation systems emerged as the times require. Recommendation systems, as an important tool to help users to filter internet information, play an extremely important role in both academia and industry. The traditional recommendation system assumes that all users are independent. In this paper, in order to improve the prediction accuracy, a recommendation system based on space-time user similarity is proposed. The experimental results on Sina Weibo dataset show that, compared with the traditional collaborative filtering recommendation system based on user similarity, the proposed method has better performance in precision, recall and F-measure evaluation value.
  Keywords: time-based user similarity; space-based user similarity; recommendation system; user preference; collaborative filtering.
  
  
• Joint end-to-end recognition deep network and data augmentation for industrial mould number recognition  
  by RuiMing Li, ChaoJun Dong, JiaCong Chen, YiKui Zhai 
  Abstract: With the booming manufacturing industry, the significance of mould management is increasing. At present, manual management is gradually eliminated owing to need for a large amount of labour, while the effect of a radiofrequency identification (RFID) system is not ideal, which is limited by the characteristics of the metal, such as rust and erosion. Fortunately, the rise of convolutional neural networks (CNNs) brings down to the solution of mould management from the perspective of images that management by identifying the digital number on the mould. Yet there is no trace of a public database for mould recognition, and there is no special recognition method in this field. To address this problem, this paper first presents a novel data set aiming to support the CNN training. The images in the database are collected in the real scene and finely manually labelled, which can train an effective recognition model and generalise to the actual scenario. Besides, we combined the mainstream text spotter and the data augmentation specifically designed for the real world, and found that it has a considerable effect on mould recognition.
  Keywords: mould recognition database; text spotter; mould recognition; data augmentation.
  
  
• Implementation and evaluation of a gesture-based virtual reality system for dementia prevention  
  by Kaisei Komoto, Naho Kuriya, Tomoyuki Ishida 
  Abstract: Japan is a super-aging society with the number of patients with dementia rising annually underscoring the crucial need for dementia prevention. Among various preventive methods, a method known as cognicise is gaining popularity. The term “cognicise” combines the words “cognition” and “exercise.” Towards dementia prevention, we developed a gesture-based virtual reality (VR) system that utilizes a depth camera and a stereo hand-tracking camera. The depth camera captures the player’s real-space walking movements and synchronizes them with a virtual avatar’s actions in the VR world. Additionally, the stereo hand-tracking camera recognizes the player’s hand gestures for playing the popular game rock-paper-scissors with a computer-generated virtual avatar. This system allows players to gamify their experience by engaging in rock-paper-scissors while walking through an immersive VR world. Although the system received high ratings across multiple evaluation criteria, specific issues were identified regarding the operability of the walk-through function.
  Keywords: dementia prevention; cognicise; virtual reality; gesture recognition.
  DOI: 10.1504/IJGUC.2025.10077271
   
  
• Application of improved PBFT based on double layer structure in enterprise supply chain information management  
  by Jiangna Liu, Yuxia Song, Congwei Zhang, Fei Guo 
  Abstract: In liquor enterprises, the traditional supply chain system information is centrally managed, which carries high risks. Therefore, it is necessary to upgrade the management methods. To improve the security of supply chain management in liquor enterprises, this study proposes to optimise the Practical Byzantine Fault Tolerance using a double layer structure and apply it to the supply chain management system. The optimisation process first divides the network nodes into multiple layers and then communicates based on the hierarchical nodes to achieve the effect of optimising communication complexity and improving security. Finally, the optimisation algorithm is applied to performance analysis in enterprise supply chain management. The experimental results showed that the improved Byzantine-fault Tolerance using a double layer structure could not only achieve a throughput of 2872 Tps when the number of nodes was 90 but also achieve a minimum latency of 0.43 s. Applying this algorithm to the system could achieve a maximum malicious node tolerance of 3374, and the application satisfaction score of different system modules could reach over 80 points. Therefore, the improved algorithm constructed in this study has excellent information management performance in the supply chain of liquor enterprises.
  Keywords: double layer structure; practical Byzantine fault tolerance; supply chain; blockchain technology; information management.
  DOI: 10.1504/IJGUC.2025.10077558
   
  
• A soldering motion analysis system for monitoring whole body of workers during soldering operation: evaluation for different scenarios  
  by Tetsuya Oda 
  Abstract: Soldering is one of the industrial techniques required in electronic device manufacturing plants to solder electric circuits which affects product quality. However, there are some danger situations or accidents during soldering for people with Autism Spectrum Disorder (ASD), Attention Deficit Hyperactivity Disorder (ADHD) and Motor Disability (MD). In this paper, we propose a soldering motion analysis system to estimate the movement of a worker during soldering operation while seated in a chair. We considered three scenarios the safety movement, the general dangerous movement and the dangerous movement caused by characteristics of a person with disabilities during soldering. The performance evaluation shows that the proposed system is capable to recognize the body movements images by RGB-D camera. Also, the proposed system can assist beginners and persons with disabilities for safe soldering operations.
  Keywords: soldering; motion analysis; people with developmental disabilities; movements of soldering.
  DOI: 10.1504/IJGUC.2024.10077840
   
  
• The extent of awareness of the teaching staff members at the University of Samarra of the technology (hologram) in the teaching process  
  by Abdul Munem Hasan Ahmed Ali, Husam Abdulhameed Hussein, Raed Ashraf Kamil Albadri, Shihab A. Shawkat, Abdulsattar Abdullah Hamad Mohamad 
  Abstract: The current study sought to introduce the concept of hologram technology and its importance in the educational field and what the advantages are of employing it in the educational process, as well as identifying its types and characteristics, as well as identifying the applications of hologram technology in education, as well as identifying the most important challenges and difficulties facing teachers in applying this technology. In addition to identifying the technology of cloud computing and its importance in the educational process, the researcher used the descriptive approach in his study. The study sample consisted of (60) faculty members at Samarra University who were selected from all faculties of Samarra University. The researchers used the statistical software (Spss20) in order to examine the differences between the responses of the study sample members.
  Keywords: hologram technology; teaching; cloud computing; teaching process.
  DOI: 10.1504/IJGUC.2025.10078031
   
  
• Dynamic parameter optimisation method for database based on large language model and evolutionary reinforcement learning  
  by Lihua Pan, Jin Li 
  Abstract: This study proposes an intelligent tuning framework that integrates large language models with evolutionary reinforcement learning for dynamic database parameter optimisation. By leveraging the semantic understanding of LLMs for initialisation, exploration guidance, and adaptive reward weighting alongside evolutionary strategies, the framework enables efficient online adaptation in high-dimensional parameter spaces. Validated across OLTP, HTAP, and cloud-native scenarios, the method improves throughput by 96.9%, reduces latency by 54.1%, and enhances resource utilisation by 28.7% compared to conventional reinforcement learning, while also accelerating convergence and reducing total tuning time. Ablation studies confirm the critical contribution of LLM-driven collaborative mechanisms to overall performance gains.
  Keywords: large language model; evolutionary reinforcement learning; database parameter tuning; dynamic optimisation; intelligent decision-making; performance optimisation.
  DOI: 10.1504/IJGUC.2026.10078071
   
  
• GLE: an important patentee identification method based on comprehensive structural entropy  
  by Na Deng, Jiu-an Zhang 
  Abstract: Promoting patent cooperation among universities, enterprises, and research institutes transforms academic knowledge into scientific achievements, driving industrial innovation. Identifying important nodes (patentees) in patent cooperation networks allows public resources to support core patentees, improving Industry-University-Research (IUR) cooperation efficiency. We reframe this as a node importance identification problem within patent innovation networks. Since existing algorithms rarely consider both global and local network topology simultaneously, we propose an improved structural entropy algorithm to identify core patentees. The method computes weighted centrality based on node degree and strength, calculates local structural entropy, and incorporates global position information via the K-shell method. Node importance is then determined by combining local structural entropy with neighbouring node contributions. Using a patent cooperation network of Hubei universities, the SIR propagation model and Kendall correlation coefficient validate our approach. Results confirm the method evaluates node importance more effectively and accurately than existing algorithms.
  Keywords: patent collaboration network; node importance; structural entropy; weighted complex network; SIR.
  DOI: 10.1504/IJGUC.2024.10078257
   
  
• Visual information extraction-based multi-source data visualisation analysis technology for digital media  
  by Yunying Wang 
  Abstract: The advancement of information technology has led to the continuous enrichment of digital media technology, making accurate extraction and visualisation analysis of visual information increasingly important. To address the poor accuracy in current information extraction methods, this study uses OCR technology to extract visual information and proposes a bidirectional transformer BiLSTM-CRF model to extract entity information. This model constructs a digital media Knowledge Graph (KG) and designs an entity alignment method based on GRN to develop a digital media visualisation analysis system. The proposed entity information extraction model was compared with other models in terms of performance. It was found that the precision and AUC values of the model were 97.57% and 0.978, which were greater than other models. The average MSE and RMSE values were 1.675 and 1.294. In addition, the designed digital media multi-source data visualisation analysis system has demonstrated good performance in application effect analysis. The CPU occupancy rate of this system was 42.38%, which was better than the comparison system. The results indicate that the constructed information extraction model and visualisation system are effective and of practical value, and can provide a theoretical basis for research fields related to digital media technology.
  Keywords: digital media; multi-source data; visual analysis; visual information extraction; optical character recognition technology.
  DOI: 10.1504/IJGUC.2026.10078260
   
  
• Smart library retrieval method based on feature fusion and FCN  
  by Xianghu Ye 
  Abstract: Smart libraries contain massive amounts of multimodal data such as text, images, and lighting. However, current cross-modal retrieval algorithms suffer from loss of detailed information, insufficient semantic correlation between modalities, and imbalanced retrieval efficiency and accuracy, which seriously affect the service effectiveness of smart libraries. Therefore, the study proposes a smart library retrieval method based on feature fusion and fully convolutional networks. This method first extracts global features of the text through Word2vec, and uses a fully convolutional network to extract pixel level multi-scale features of the image. The dynamic similarity matrix is applied to calibrate semantic associations. The research findings denote that in the Flickr-25k dataset and the wide dataset of the National University of Singapore, the recall rates of cross-modal retrieval methods based on feature fusion and fully convolutional networks in the top 10 are 90.4% and 81.6%, respectively. The average precision under 128-bit input is 90.2% and 88.7%, respectively, with time thresholds of 1.11 s and 1.15, which are better than other algorithms. The actual application test results show that the highest error rate of this method is only 0.61%, the bounce rate is as high as 98.0%, the retrieval accuracy is between 98.0% and 99.8%, and the storage and response performance are excellent. The above results indicate that the cross-modal retrieval method based on feature fusion and fully convolutional networks can provide efficient technical solutions for cross-modal retrieval in smart libraries.
  Keywords: smart library; feature fusion; fully convolutional network; cross-modal retrieval.
  DOI: 10.1504/IJGUC.2026.10078884
   
  
• Unveiling mobile health monitoring system adoption in Iraq: a dual-factor analysis of enablers and inhibitors impacting user intentions  
  by Mohamed Asem, Mohmed Y. Mohmed Al-Sabaawi, Ramadan Ramo, Ali Abdulfattah Alshaher 
  Abstract: The Mobile Health Monitoring Systems (MHMS) has developed as an innovative solution for improving healthcare services delivery, especially in developing Iraq. The current study examines the MHMS adoption in Iraq. It proposed a research model by applying a dual factor approach that examines both enablers and inhibitors influencing user intentions toward adopting MHMS. The study relied on UTAUT to identify the enabler factors. And it depends on the Status Quo Bias (SQB) theory to determine the barriers. The questionnaire used for data collection. The results showed that performance expectancy, facilitating conditions, and social influence have an important influence on user intention toward MHMS adoption. Whereas inertia and sunk costs were considered as key barriers. Regarding effort expectancy and transition costs, they did not have a significant influence. These findings offer valuable guidance for healthcare professionals and tech companies in Iraq and similar developing countries to improve mobile health system adoption.
  Keywords: mobile health monitoring systems; technology adoption; dual-factor approach; UTAUT; status quo bias; developing countries.
  DOI: 10.1504/IJGUC.2026.10079007
   
  
• Unified execution of scientific workflows: a federated approach in the cloud-edge continuum  
  by Vojdan Kjorveziroski, Anastas Mishev, Sonja Filiposka 
  Abstract: Workflow management systems (WfMS) are a cornerstone of workflow execution and an essential tool for scientific research. Existing WfMS offer limited customisability of the execution environment, support only proprietary workflow definition languages, or lack robust scaling mechanisms. To overcome these issues, we present a federated WfMS developed on top of standardised and reusable components. We describe the extension of the popular REANA WfMS so that it can be deployed in a federation of Kubernetes clusters, gaining the capability to schedule scientific workflows across the resulting computing federation. Furthermore, we introduce support for a completely new runtime environment in addition to containers WebAssembly. The proposed design of the federated workflow management system is modular and based on open-source components, making it easily extensible in the future. The federated WfMS has been validated in practice with workflow execution environments deployed in two countries, leveraging four independently deployed Kubernetes clusters.
  Keywords: workflow management systems; scientific workflows; compute federations; containers; orchestration; WebAssembly; cloud-edge continuum.
  DOI: 10.1504/IJGUC.2026.10079037
   
  
• Distributed network security authentication mechanism integrating blockchain and artificial intelligence  
  by Long Li, Jinka Wang, Junli Luo 
  Abstract: This paper proposes BlockGrad, a blockchain-based deep learning framework that enhances federated learning security by integrating Byzantine Fault Tolerance (BFT) consensus and reputation-based weighted aggregation. Unlike traditional methods such as Federated Averaging and Multi-Krum, BlockGrad combines gradient validation, reputation evaluation, and dynamic node replacement into a closed-loop defence mechanism. Through clustering-based gradient screening and weighted aggregation, the framework effectively mitigates the impact of malicious participants. Simulation results under a 30% malicious-node attack demonstrate that BlockGrad achieves higher and more stable classification accuracy than Federated Averaging, showing strong robustness in adversarial environments. The proposed approach also enables decentralised trust management and long-term behavioural tracking, which are absent in many existing robust aggregation methods. Furthermore, the computational overhead of BlockGrad is analysed, and its applicability to large-scale distributed systems is discussed. Future work will focus on improving scalability, privacy protection, and algorithmic efficiency.
  Keywords: blockchain; artificial intelligence; deep learning; Byzantine fault tolerance; distributed network security.
  DOI: 10.1504/IJGUC.2026.10079272
   
  

Special Issue on: Cloud and Fog Computing for Corporate Entrepreneurship in the Digital Era

• Study on the economic consequences of enterprise financial sharing model  
  by Yu Yang, Zecheng Yin 
  Abstract: Using enterprise system ideas to examine the business process requirements of firms, the Financial Enterprise Model (FEM) is a demanding program. This major integrates finance, accounting, and other critical business processes. Conventional financial face difficulties due to low economic inclusion, restricted access to capital, lack of data, poor R&D expenditures, underdeveloped distribution channels, and so on. This paper mentions making, consuming, and redistributing goods through collaborative platform networks. These three instances highlight how ICTs (Information and Communication Technologies) can be exploited as a new source of company innovation. The sharing economy model can help social companies solve their market problems since social value can be embedded into their sharing economy cycles. As part of the ICT-based sharing economy, new business models for social entrepreneurship can be developed by employing creative and proactive platforms. Unlike most public organizations, double-bottom-line organizations can create social and economic advantages. There are implications for developing and propagating societal values based on these findings.
  Keywords: finance; economy; enterprise; ICT; social advantage.