International Journal of Web and Grid Services (7 papers in press)

Regular Issues

• Bi-Phase LSTM: A LSTM-Based Autoencoder Architecture for Dynamic Social Network Prediction  
  by Hui Lin, Yi-Cheng Chen 
  Abstract: In recent years, social networks have grown in popularity, with most people actively engaging on these platforms. These networks hold valuable insights into users’ values and interests, allowing us to analyse relationships between connected individuals and even predict potential friendships. However, social networks are dynamic, and their structure evolves over time. To account for this, we employed a dual approach using a bi-phase LSTM autoencoder and a bi-phase LSTM predictor. These tools capture the changing characteristics of social networks and predict future graph structures. We rigorously tested our model on three datasets and compared its performance with other models. The bi-phase LSTM consistently delivered strong results across all datasets. Additionally, the model’s hyperparameters were fine-tuned to improve predictive accuracy, demonstrating its reliability in forecasting the evolution of social network structures.
  Keywords: feature extraction; autoencoder; decoder; long short-term memory; dynamic social network.
  DOI: 10.1504/IJWGS.2025.10068502
   
  
• Adaptive Proportional-Derivative Adjuster for Notch Filtering in Wearable ECG Monitoring  
  by Chao-Ting Chu, Jiawei Chang 
  Abstract: This paper presents an adaptive proportional-derivative adjuster (APDA) integrated into a notch filter for processing ECG signals in wearable smart clothing. The APDA filter dynamically adjusts parameters such as gain and cutoff frequency in real time to mitigate environmental interference, including 60 Hz noise and electromyographic signals common in workplaces and fitness centres. Unlike traditional fixed-parameter filters, this adaptive method minimises noise and preserves ECG clarity under varying conditions. A notable contribution of this study is optimising the APDA algorithm for resource-constrained microcontrollers, reducing both memory requirements and processing power. This streamlined computation lowers complexity and extends battery life, making it suitable for continuous, long-term monitoring. Experimental results from a smart clothing prototype validate the filters effectiveness in suppressing noise while maintaining signal integrity, offering an energy-efficient and cost-effective solution for wearable healthcare applications. This advancement addresses the limitations of conventional designs and shows promising potential for future clinical applications.
  Keywords: adaptive filtering; proportional-derivative control; wearable ECG monitoring; real-time noise suppression; sustainable healthcare technology.
  DOI: 10.1504/IJWGS.2025.10069918
   
  
• Improved Simplified Swarm Optimisation for Bipartite Graph Convolutional Network  
  by Zhenyao Liu, Wei-Chang Yeh 
  Abstract: Bipartite graphs have been widely applied in data mining to represent data relationships, such as in e-commerce recommendation systems. Graph neural networks (GNNs), with their powerful ability to process structured data and explore higher-order information, have become the state-of-the-art method for recommendation problems. Recommendation systems increasingly rely on graph structures to represent relationships between users and items, like user click behaviours and purchase records. Through graph convolutional networks (GCNs), these structures capture connections between users and items, integrating structural information (e.g., user-item links) with node features (e.g., user preferences and item attributes) for accurate recommendations. This study combines improved simplified swarm optimisation (iSSO) with bipartite graph convolutional networks and eye-tracking technology to explore user preference behaviour, called iSSO-BGCN. We construct a node-feature bipartite graph, using iSSOs optimisation capabilities and natural gradient descent to train the model. Trials validate its ability to deliver precise recommendations.
  Keywords: Graph Neural Networks; Graph Convolutional Networks; Improved Simplified Swarm Optimization; Bipartite Graph; Recommendation System.
  DOI: 10.1504/IJWGS.2025.10070494
   
  
• Enhancing Environmental Education through Virtual Reality: a Case Study in Primary Marine Ecology Learning  
  by Hsuan-Che Yang 
  Abstract: This study uses virtual reality technology to create digital teaching materials for primary school students on marine ecology and environmental education. These materials enhance learning motivation while conveying information about endangered marine organisms. Through an immersive VR diving experience, students can observe the habits and threats faced by these creatures. The study includes four games that focus on ecological issues and pollution along Taiwans east and west coasts, developed in collaboration with an elementary school in Danshui using the ADDIE instructional design model. A pre-test was conducted before introducing the VR system to evaluate progress in two classes. Results showed that the class using the VR system improved more in the post-test than the one receiving the traditional way. Although the improvement was not statistically significant, feedback from both students and teachers indicated a positive response, suggesting that this approach benefits students with weaker foundational knowledge.
  Keywords: Virtual Reality; Meta Quest 2; Environmental Education; Marine Ecology; Instructional Design.
  DOI: 10.1504/IJWGS.2025.10071216
   
  
• 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.
  
  
• Real-Time System for Detecting High-Emission Diesel Vehicles Using Deep Learning  
  by Yu Yu Yen, Chih-Chun Chiu, Pin-Hao Huang, Jui Hung Kao 
  Abstract: In recent years, air pollution emission statistics in Taiwan have indicated that mobile sources contribute the largest share of pollution in metropolitan areas. As a result, developing an intelligent, fully automated system for identifying high-emission diesel vehicles has become a critical necessity. The development of a high-pollution vehicle detection system utilises a one-stage architecture. A YOLOv4-based neural network module has been implemented to extend its application. The real-time image data of each vehicle is processed and optimally integrated through data augmentation, algorithm optimisation, and image enhancement. This enables the system to effectively identify high-pollution vehicles from complex, real-time traffic flow imagery and capture relevant vehicle information. Using these inputs, the system demonstrates enhanced adaptability to diverse environments. Furthermore, the system uses multiple image datasets for augmentation, incrementally improving accuracy. The simulation results indicate that the system achieves a detection accuracy that exceeds 91%, particularly for high-polluting diesel vehicles.
  Keywords: deep learning; object detection; diesel vehicle pollution detection; high pollution emission monitoring system.
  DOI: 10.1504/IJWGS.2025.10073456
   
  
• Predicting E-commerce Customer Churn Using a PCA-AdaBoost Combined Model  
  by Yang Ding 
  Abstract: Customer loyalty is closely related to the development of e-commerce platforms, but due to the non-contractual characteristics of e-commerce users and the poor performance of traditional customer data analysis, the phenomenon of customer churn is more prominent and obvious. Therefore, based on this, a combination prediction model is proposed to analyse customer data, which optimises indicator data on the basis of recency, frequency, and monetary models. By adding emotional feature indicators, customer rating indicators, and introducing an improved K-value clustering algorithm, the problem of customer churn prediction is analysed. Subsequently, principal component analysis is used to reduce the dimensionality of the data and combined with adaptive boosting algorithms to better ensure classification accuracy. The results show that the overall accuracy of the combined algorithm on the dataset is above 98%, significantly superior to other algorithms, and its recall results for non-churn customers are also above 97%, with a mean absolute percentage error of less than 2%. The specific stability and fitting are good, with the overall accuracy value and consistency coefficient basically below 0.02. This combination prediction model can effectively provide reference value for e-commerce operators to improve customer relationship management and reduce customer churn issues.
  Keywords: E-commerce; RFM model; PCA; AdaBoost algorithm; Customer churn; Self organizing mapping; K-means clustering.
  DOI: 10.1504/IJWGS.2025.10073458