International Journal of Web Engineering and Technology (7 papers in press)

Regular Issues

• Load Balancing and Auto-Scaling Issues in Container Microservice Cloud-Based (CMCB) System: A Review on the Current trend technologies  
  by Shamsuddeen Rabiu, Chan Huah Yong, Sharifah Mashita Syed-Mohamad 
  Abstract: Load balancing and auto-scaling are essential to cloud features for cloud-based container microservices as they control the number of computing resources available. Many research works have proposed load balancing and auto-scaling approaches for microservices individually, however, less likely concerned to propose the two approaches in solving their problems simultaneously. The paper aimed to critically analyse the current issues related to load balancing and auto-scaling in container microservices cloud-based systems. This will open room for researchers in the field to enhance performance for better QoS to the users. We present a comprehensive literature review of the existing techniques used for load balancing and auto-scaling in cloud-based containerised microservice applications. After the in-depth review, it is found that load balancing and auto-scaling contribute as a value-added feature to the microservice applications. This can optimise the issues of Servers overloaded, service failure, traffic spikes, et cetera, during the microservices communication phase.
  Keywords: microservice; docker; container; cloud-based; load balancing; auto-scaling; quality of service; QoS; algorithm; QoS metrics.
  DOI: 10.1504/IJWET.2023.10058314
   
  

Special Issue on: New Trends in Knowledge Management Development

• A study on the economic and sustainable development forecast of rural tourism industry based on ANN  
  by Li Huang, Jingwei Zhai 
  Abstract: This study establishes a rural tourism industry economic sustainability prediction model based on the back propagation neural network (BP) in artificial neural network (ANN). It selects the indicators that have a large influence on the rural tourism industry economic sustainability prediction, and takes the four indicators with the highest weight percentage as the input of the prediction model, and verify the validity of the model. The result shows that the average relative prediction error of the univariate BP neural network was smaller than the grey model (GM). The average absolute value of relative prediction error for the multivariate BP neural network was smaller than the prediction error value of the univariate BP neural network model. The AUC value of the multivariate BP prediction model based on this study is 0.93. This research model improves the accuracy of predicting the sustainable economic development of the rural tourism industry.
  Keywords: artificial neural network; ANN; rural tourism; BP neural network; economic forecasting; sustainable development.
  DOI: 10.1504/IJWET.2023.10059296
   
  
• Predicting the enterprise tax risk using improved multilayer perceptive vector machine  
  by Yi Liu 
  Abstract: With the comprehensive promotion of the business tax to value-added tax policy, the tax burden of enterprises is gradually reduced. Although office informatisation is progressing quickly, managing enterprise tax risk is still crucial. Multilayer perceptron can be combined with support vector machine to form multilayer perceptron vector machine. Therefore, the study uses the genetic algorithm to improve the multilayer perceptive vector machine, and on this basis, establishes the enterprise tax risk prediction model to improve the accuracy of tax risk prediction. According to experiment results, the CNN prediction model's accuracy in predicting economic risk, competitive risk, policy risk, and business risk is only 84.37%, while the accuracy of the improved algorithm was over 90% in all cases, with the accuracy of policy risk being as high as 95.87%. The results indicate that the improved algorithm can accurately predict the tax risks of enterprises, providing an effective method to guarantee the security of enterprise tax management.
  Keywords: support vector machine; multilayer perceptron; genetic algorithm; tax risk.
  DOI: 10.1504/IJWET.2023.10059297
   
  
• Research on the privacy protection model of government cyber security in smart cities based on big data  
  by Gongping Chen, Hong Wang 
  Abstract: With the escalation of hacking methods, the existing network security privacy model can no longer fully guarantee the security of private information. To solve the problem of poor security performance of the traditional privacy protection model, the research proposes an improved privacy protection algorithm based on the SMART algorithm by optimising the hierarchical processing of the original sensing data, which encrypts and protects the private data, and embeds the privacy protection algorithm into the government network security privacy protection model. The experimental results show that proposed algorithm has a privacy exposure probability of 0.05, a fusion accuracy of 89% and a network energy consumption of 82.5%, which is all better than comparison algorithms. It can provide better security protection to the government cybersecurity privacy protection model, and also provide a new idea for the privacy protection method of the privacy protection model.
  Keywords: network security; privacy protection; SMART algorithm; D-SMART algorithm; fusion accuracy.
  DOI: 10.1504/IJWET.2023.10059298
   
  
• Research on the application of association rules based on information entropy in human resource management  
  by Yi Wang, Lei Li 
  Abstract: The informatisation process of human resource management requires the face of massive data, and association rule algorithms can efficiently mine the relationships between itemsets from massive data. The Apriori algorithm is widely used due to its advantages such as simple operation, but it is prone to generating a large number of candidate itemsets and fails to consider the differences in the importance of different attributes. To solve the above problems, a genetic algorithm is proposed to optimise association rules, and then an incremental association rule mining algorithm is constructed by combining it with information entropy improved by mutual information method. The experimental results show that when processing the data set Q with a large amount of data, the speedup ratio of the PARIMIEG algorithm is better than other algorithms in different stages, the highest is 2.3, and the accuracy rate is 92.5%. The PARIMIEG algorithm can be applied to the performance index assessment of enterprises, personnel, and talent selection in subsequent human resource management. It is an excellent tool to improve the company's human resource management level and promote the development of the market economy.
  Keywords: association rules; human resources; information entropy; technology fusion; genetic algorithm.
  DOI: 10.1504/IJWET.2023.10059299
   
  
• Personalised learning systems: drivers of employees' behavioural intention  
  by Sandra Schlagheck, Gerhard Schewe 
  Abstract: Knowledge management is essential for achieving and maintaining competitive advantage. This can be fostered by learning activities. Due to personalisation, learning materials can be tailored to the learners' needs and, thus, improve effectiveness and efficiency. To successfully implement such systems, users' acceptance is crucial. However, which factors affect the intention to use personalised learning systems remains unclear. By applying the unified theory of acceptance and use of technology, we explore factors influencing the intention to use them. Using a quantitative cross-sectional survey, 331 German employees from various industries and positions are asked. A structural equation model with maximum likelihood estimation is chosen for the analysis. Three potential moderators (gender, age, and experience) are examined based on multi-group analyses. Our results suggest that behavioural intention is mainly driven by the expected performance and the anticipated pleasure of using the system. Performance expectancy fully mediates the influence of trustworthiness on intention.
  Keywords: behavioural intention; corporate learning; employees; knowledge management; moderation analysis; personalised learning systems; PLS; structural equation model; SEM; technology acceptance; trustworthiness; UTAUT2.
  DOI: 10.1504/IJWET.2023.10057560
   
  
• Application of chorus teaching model for pedagogical quality assessment on software engineering skills teaching  
  by Qidong Kang 
  Abstract: Currently, many software engineering students lack skills at a professional level. To address this issue, a chorus teaching quality evaluation model is constructed and improved to enhance software engineering students' understanding and mastery of relevant knowledge. An adaptive variational genetic algorithm (GA) is proposed to overcome the limitations of traditional GA with fixed variation probability. The improved GA is employed to optimise the BPNN, resulting in the AGA-BP algorithm. The entropy method (EM) is introduced to avoid subjective pedagogy in BPNN, and an EM-AGA-BP-based chorus class pedagogical quality assessment model is constructed. Research results show that the accuracy of the pedagogical quality assessment model utilising EM-AGA-BP algorithm reaches 99.84%, SSE value converges to 0.21, fitness value is 1.20, and AGA-BP model's F1 value is 0.84, all of which outperform other models significantly. The model shows desirable accuracy, thereby enabling software engineering students to gain more and improve their skills.
  Keywords: pedagogical quality assessment; GA; BPNN; software engineering; entropy method; EM.
  DOI: 10.1504/IJWET.2023.10059302