International Journal of Computational Systems Engineering (20 papers in press)

Regular Issues

• Open Access

  The Role of Modular MOOCK Design Based on Empirical Learning in Printmaking Teaching ( Free Full-text Access )

  by Hongyan Chi, Kai Pan 
  Abstract: The development of technology and teaching philosophy brings new insights to art teaching, especially module teaching which is difficult to materialize and can cultivate students’ relevant literacy through meaning and scene construction in other ways. The teaching of printmaking is divided into two modules, technique, and art, in which art education is closely linked to teachers’ teaching concepts and approaches, so drawing on excellent teaching concepts and art cultivation is the key to overcoming the difficulties of teaching printmaking. The study constructs and optimizes the catechism recommendation method, which combines knowledge points, courses, and student characteristics for course recommendation. The results show that the method has higher performance parameters than the traditional method, including an AUC value of 40.52% higher than the traditional method, which indicates that the accuracy of the method is better than that of the traditional method. The constructed algorithm will be used in the teaching of the catechism, and the teaching role of the catechism will be evaluated through a semester-long comparison experiment.
  Keywords: Empirical learning; Modular; MOOC; Hierarchical analysis; Pedagogical model.
  DOI: 10.1504/IJCSYSE.2026.10075797
   
  
• Improve Text Classification Accuracy by Using Fuzzy-Convolutional Neural Network Model  
  by Xuan Wang, Jing Su 
  Abstract: Most of the text data we can see in daily life is fuzzy, which fuzzy information will increase the noise and reduce the classification accuracy. In order to solve this situation, this paper proposes a network model that fuses fuzzy neural network (FNN) and convolutional neural network in text classification (TextCNN), namely text fuzzy-convolutional neural network (TextFCNN). Firstly, the model uses FNN and TextCNN to obtain two sets of classification results; secondly, the fuzzy inference system is combined to further eliminate the fuzzy characteristics and achieve more correct classification outcomes. In the movie review (MR) dataset, the model was improved by 1.41% and 6.38% in accuracy compared to the single neural network FNN and TextCNN, respectively. Compared with other text classification methods, the accuracy of TextFCNN is improved by 0.33% 3.19%. Experimental results show that the network model TextFCNN can indeed improve the effect of the classifier.
  Keywords: text classification; fuzzy neural network; FNN; convolutional neural network; fuzzy theory; natural language processing; NLP.
  DOI: 10.1504/IJCSYSE.2027.10063460
   
  
• Data Collection and Protection of Personnel Evaluation under Differential Privacy  
  by Yue Wu, Yaping Pan, Gang Wang, Shenghong Wang, Zhenfen Zhang 
  Abstract: This article utilized DP (differential privacy) technology to ensure that sensitive information of individuals was effectively protected during data collection and processing. Firstly, it used the LN (Laplace Noise) distribution to perform DP protection on the raw data, and compared it with exponential noise and Gaussian noise. Secondly, it divided the data into unrelated groups, added noise to each group, and adjusted DP parameters to balance data protection and data availability. Then, this article utilized the GD (Gradient Descent) algorithm to optimize parameters to maximise data availability and allocate privacy budgets to different data processing operations. Finally, during the data collection process, this article randomly selected samples and introduced random trap data points to reduce the risk of individual identification. It used metrics such as information loss and KL (Kullback Leibler) divergence to evaluate the degree of privacy leakage in DP protection.
  Keywords: Data Privacy Protection; Differential Privacy Techniques; Information Noise Addition; Privacy Measurement Metrics; Individual Identification Risk.
  DOI: 10.1504/IJCSYSE.2027.10064042
   
  
• Personnel Evaluation of Data Encryption Transmission and Storage Technology for Cloud Computing Environment  
  by Xu Zhang, Peidong Du, Qingzhao Hu, Zuohu Chen, Miao Wang, Long Wang 
  Abstract: In response to the current evaluation by personnel that data encryption transmission and storage technology has problems such as limited storage space resources, slow encryption speed, and low encryption accuracy. This article studied the existing problems in the cloud computing environment. In the cloud computing environment, stream cipher encryption methods were utilised to encrypt movie evaluation data, and combined with chaotic sequence systems, the encryption and decryption process of the data was completed. Then, transport layer security protocols and hash functions were utilised to verify user data and ensure data integrity. At the same time, data storage technology in cloud computing systems was studied, and unstructured storage technology was utilised to store evaluation data, effectively improving the speed of data storage. The encryption accuracy of data transmission obtained by the stream cipher encryption method was above 96.85%, and the average encryption accuracy of 50 experiments was 97.95%, which was 9.01% higher than the average encryption accuracy of the digital signature algorithm method. In response to the problem of limited storage space resources in cloud computing environments, this article utilised stream cryptography and unstructured storage technology to effectively ensure the security of data transmission and improve the space and speed of data storage.
  Keywords: unstructured storage technologies; USTs; evaluation of data; encrypted transmission; cloud computing environments; stream cipher; homomorphic encryption.
  DOI: 10.1504/IJCSYSE.2027.10064044
   
  
• The Regulation Method of Agricultural Internet of Things Services Based on Dynamic multi-objective Optimization  
  by Chaoqun Huang, Qianlan Liu, Wenbin Qian 
  Abstract: In response to the complex and ever-changing environmental impacts faced in the current construction of agricultural internet of things technology. A supervision method for agricultural internet of things services based on dynamic multi-objective optimisation is proposed. The poor dynamic capabilities in the intelligent agricultural internet of things can be solved by constructing a decomposed algorithm. According to the findings, it performed well in convergence, hypervolume value and extreme point accuracy. This algorithm could propose the optimal service matching scheme based on a single-target service strategy, with good diversity. In addition, the calculation time of this algorithm was relatively short. Compared with the other two comparison methods, it led by 3.59s and 8.39s, respectively. Meanwhile, the average service cost of this algorithm was relatively low. It reduced the average service cost by 16.39% and 25.00%, respectively. Overall, the dynamic multi-objective optimisation agricultural internet of things regulation method has performed well in practical application, significantly improving accuracy. It can provide the highest quality service at the lowest cost within the shortest service time. In summary, this research provides an effective solution for the regulation of internet of things services in the intelligent agriculture.
  Keywords: internet of things; IoT; MOO algorithm; dynamic multi-objective optimisation algorithm; agriculture.
  DOI: 10.1504/IJCSYSE.2027.10064212
   
  
• Design and Management of Enterprise E-commerce Financial System Based on Machine Learning  
  by Li Fu, Yi Yao 
  Abstract: The rapid development of network technology makes it closely related to peoples daily life, from the increasing number of users to the rapid development of express delivery industry, it shows the convenience brought by the network to human beings. In todays world where almost everyone is shopping online, this is both an opportunity and a huge challenge. In the fierce competition in the e-commerce market, how to retain users and attract more new users has become the key to its development. Today, with the rapid development of the internet and artificial intelligence, the competition of e-commerce is ultimately a contest of technology. Whoever can make their products more intelligent, more convenient and more accurate can occupy a place in this industry. This paper mainly studies the problems existing in the e-commerce management system, and proposes an artificial intelligence-based machine learning method to establish a users behaviour model and predict it. On this basis, it is combined with the traditional ant algorithm, and the learning method in the model framework is compared with XGBoost algorithm. The results showed that the optimised XGBoost algorithm had a good application prospect, and its prediction accuracy exceeded 85%.
  Keywords: Enterprise E-commerce System; Machine Learning; Order Management; B/S Mode; Support vector machine.
  DOI: 10.1504/IJCSYSE.2027.10066185
   
  
• Wireless Network Intrusion Detection using Feature Sampling and Selection Approach in an IoT Environment  
  by Zhujia K.  
  Abstract: It will be necessary to offload a large amount of computing tasks onto edge servers in order to keep up with the growing demand for IoT applications that utilise edge computing. In turn, this will help companies meet the surging demand for these apps. As soon as data transfer begins, this safeguard must kick in. The researchers in this study built a multi-attack intrusion detection system (IDS) for edge-assisted internet of things (IoT) using a BP neural network and an RBF neural network. To identify the anomaly and prioritise the attributes for each attack, the BP neural network's capabilities are utilised to their fullest potential. The goal of detecting infiltration by several attacks required the construction of a neural network based on the radial basis function (RBF). In the proposed multi-attack scenario, the results likewise show a high level of accuracy.
  Keywords: internet of things; IoT; neural network; multi-classification; intrusion detection system; IDS; network attacks; false positive rate; undetected rate.
  DOI: 10.1504/IJCSYSE.2027.10066357
   
  
• An Approach to Security Evaluate Crucial Data Stored in a Cloud Platform Using BCSS Technique  
  by Rajkumar Veeran, Priyadharshini G 
  Abstract: The rise of malicious attacks like ransomware has made data security and privacy a critical challenge in the digital world. In 2020, the European Medicines Agencys COVID-19 vaccine data breach highlighted this issue. To address these challenges, we propose a blockchain cloud storage system (BCSS) that integrates blockchain technology with cloud storage for enhanced security. BCSS provides tamper-proof, timestamped records without third-party interference, offering superior security compared to traditional storage methods. Our system also ensures high storage flexibility and reduced implementation costs. Experimental results show BCSS reduces computational costs by 35.21%, increases remote access flexibility by 94.33%, and achieves a 97.43% success rate in security and maintenance, meeting the research objectives.
  Keywords: cloud storage; Blockchain; Consensus Mechanism; Security and Remote Access; Blockchain Cloud Storage System (BCSS).
  DOI: 10.1504/IJCSYSE.2027.10066360
   
  
• Exploring Aesthetic Dimensions in AI-Generated Music Compositions  
  by Huafang Liu, Zhangwei Wang 
  Abstract: The newest models of how music makes us feel (AEM) have only been around for a few years. They are based on studies from psychology and neuroscience. The main things that these models show are the thinking and processing that happens in the brain. Some of the real-world study that these models are based on, on the other hand, is related to Western tonal music. It is common for CCM to be out of tune and not organised in a way that makes sense. Through a comparison to classic-romantic music (CM), this study looked deeply into the visual parts of listening to contemporary classical music (CCM). The text was subject to a qualitative content analysis, and the groups' created main and secondary issues were tested against each other. We found big differences between CM and CCM in the areas of expectations, bodily and emotional responses and fun features.
  Keywords: AI-generated music; contemporary classical music; data augmentation data wrangling.
  DOI: 10.1504/IJCSYSE.2027.10066575
   
  
• A System of Systems ARIMAX Model of Coronavirus Propagation Dynamics on the United States East Coast  
  by Teddy Cotter 
  Abstract: During the SARS-CoV-2 coronavirus pandemic there has been a focus on forecasting the spread of COVID-19 cases. Multiple SIR model variants and time series models have been published worldwide with a goal of precisely predicting the near-term number of cases in a particular region. A major focus was on forecasting hospital bed capacity. Conversely, the dynamics of and factors contributing to or inhibiting the propagation of coronavirus have been discussed informally or assumed known with little research into their systemic effects. This research seeks to contribute to knowledge of the systemic dynamics and factors that contribute to or inhibit the propagation of coronavirus during the period March 2020 to December 2022. ARIMAX models were developed within a system of systems theoretical framework to identify the dynamics of and factors promoting or inhibiting the propagation of coronavirus on the East Coast of the United States as the system of systems of interest. Model results demonstrate that propagation dynamics vary by state within systemic states' niches in the East Coast system of systems. This system of systems time series modelling approach may be extended to modelling the propagation dynamics of future pandemic diseases.
  Keywords: coronavirus; ARIMAX; system of systems; SoS.
  DOI: 10.1504/IJCSYSE.2027.10066579
   
  
• Spatial Coupling Vibration Calculation Method of Wind-Vehicle-Bridge System based on Finite Element Model  
  by Miaoxi Yang  
  Abstract: This study suggests the Finite Element Model-based Spatial Coupling Vibration Calculation Method (FEM-SCVCM) for a convenient and comprehensive analysis of the WVB system. A spatial coupling vibration model is recommended to simulate the WVB association to resolve the vehicles' reactions efficiently and accurately. A 3D FEM considers the interaction of wind, bridges and vehicles. Furthermore, the FEM has been employed to calculate the bridge's vibration response to a variety of excitations, such as vehicle loads and wind loads. Other influence aspects like wind force, tire model, and road unevenness are considered. The results suggest that the bridge deck is the primary location of the severe vibrations. Additional bridge stresses and strains have been obtained, showing that the highest stresses occurred around the load application points, and the maximum strains occurred in the bridge's centre.
  Keywords: Finite Element Model; Spatial coupling vibration calculation method; Wind-vehicle-bridge system; Backpropagation Neural Network.
  DOI: 10.1504/IJCSYSE.2027.10066888
   
  
• A Finite State Machine Model for Mitigating Mobile Money Social Engineering Attacks  
  by Selorm Kofi Tagbo, Felix Adebayo Adekoya, Patrick Kwabena Mensah 
  Abstract: This article aims to design and propose the fundamental principles of finite state machines to build a novel mobile money fraud prevention model. The study employs a set of guidelines to construct an abstract model encompassing mapped real-life social engineering attack scenarios to suggest ways by which they can be prevented. The results obtained from the model implementation indicate that finite-state machines help in reducing social engineering attacks to a large extent. Regarding originality, while other traditional models depend on predefined systemic rules, the finite state machine model proposes an adaptable and dynamic framework, which boosts the entire fraud mitigation process. Practically, the enhanced capability of the proposed model would greatly help mobile money service providers reduce losses significantly from these attacks.
  Keywords: social engineering attack; phishing; finite state machine; FSM; mobile money fraud; financial fraud prevention; ontology.
  DOI: 10.1504/IJCSYSE.2027.10068479
   
  
• Mathematical Model Construction for Interactive Distance Learning of English at the University Level  
  by Yahui Shi  
  Abstract: To promote remote interactive learning of college English, this study focuses on English reading and constructs a corpus containing four emotions: surprise and sadness. Meanwhile, the principal component analysis method is used to optimise the emotional features of speech, and the first 19 principal components are extracted to calculate the linear contribution value of the original features. Then, the iterative binary algorithm 3 was used to synthesise evaluation indicators such as emotion and intonation, and a comprehensive evaluation model was constructed to further construct the corresponding oral learning system. The results indicate that the comprehensive evaluation models performance improved with the inclusion of emotion indicators. The accuracy increased by 12.10%, the adjacent agreement rate was 93.80%, and the Pearson correlation coefficient was 0.81. The research findings provide a methodological reference for interactive distance learning of college English.
  Keywords: University English; Distance learning; SVM algorithm; ID3 algorithm; Speech emotion; Spoken language.
  DOI: 10.1504/IJCSYSE.2027.10069441
   
  
• Research on Intelligent Clothing Design Integrating Visual Communication and Embedded System - Taking the Blind Safety Clothing as an Example  
  by Zhenzhen Sun  
  Abstract: This study aims to design an intelligent clothing that integrates visual communication. The clothing has an embedded system of alarm and safety detection, which can protect the travel safety of the blind. The result shows that the clothing has good warning function, and it still has warning effect at 30 metres without natural light. The fall detection and protection function has a separate detection module for judgment, and the judgment time is within 0.5 seconds. However, there are still shortcomings in the research and design of clothing. Due to the existence of embedded devices, intelligent clothing is less comfortable than ordinary clothing. The hardware quality of different embedded devices cannot be fully guaranteed during mass production, and some products have not been tested for their service life. In the future, user group management and services can be carried out through the cloud platform.
  Keywords: Visual communication; Smart clothing; Embedded equipment; Clothing for the blind.
  DOI: 10.1504/IJCSYSE.2027.10070035
   
  
• Learning Platform Integrating Computer Technology and RecBC Recommendation Model in the Context of Education Informatization  
  by Yanqi Ruan 
  Abstract: In order to help students get suitable courses for themselves in a huge number of online courses, the research firstly constructs a course recommendation model based on the contribution of short-term preference reconstruction behaviour, based on which computer technologies such as bidirectional long and short-term memory networks are introduced to get a recommendation model that integrates the enhancement of learning behaviours. The research results show that the sparsity of the MOOC dataset is 99.43%, which is high sparsity. And in the comparison experiments with mainstream algorithms, the recommendation model incorporating learning behaviour enhancement is more than 5% higher than other algorithms in the two evaluation indexes of hit rate and normalised discount cumulative gain. In summary, the proposed model and learning platform have good robustness and generalisation ability, and can be applied in many fields.
  Keywords: Information technology in education; Computer technology; Recommendation model; Learning platform; Short-term preference.
  DOI: 10.1504/IJCSYSE.2027.10070400
   
  
• Methods to Enhance Student Classroom Participation through Big Data and Deep Learning  
  by Mingfang Zhou, Guofang Li, Yameng Bai 
  Abstract: This study investigates the efficiency and applications of big data and deep learning in enhancing classroom engagement. Traditional teaching methods often lack personalisation, leading to passive participation. Leveraging data analytics and AI, this research identifies key engagement drivers, enabling tailored interventions for improved student involvement. A mixed method approach was adopted, combining a systematic literature review, theoretical analysis, and first-hand surveys from teachers and students. Predictive models were developed, demonstrating superior accuracy over conventional methods in assessing engagement factors. The findings provide actionable, data-driven strategies for educators to boost participation. By integrating advanced technologies, instructors can make informed decisions, fostering better learning outcomes. This study bridges theory and practice, offering a foundation for future research on AI-enhanced education.
  Keywords: Big data; Deep learning; Student participation in class; Educational technology; Data-driven instruction.
  DOI: 10.1504/IJCSYSE.2027.10072910
   
  
• A Practical Study of a Gamified Motivational Curriculum for Physical Education based on Optimal Interactive Artificial Intelligence  
  by Yan Li, Lei Yang, Yue Yin, Jingyan Sun, Jialing Yang 
  Abstract: With the rise of nationwide sports, my countrys online sports education industry has developed rapidly. However, the overabundance of courses can easily lead to user fatigue. To provide personalised, precise course services and enhance application practicality, this study combines user body and movement information with personality dynamics (PD) theory to construct an improved user model. Furthermore, an intelligent partner matching system based on convolutional neural networks was designed, and a fuzzy hierarchical evaluation index system was established. The experimental results showed that the matching accuracy, recall rate, and F1 of the intelligent schoolmate matching model IUM-SR designed in this study were 95.31%, 95.24%, and 94.17%, significantly higher than the comparison matching algorithms. Experiments verified the effectiveness of this system and index system using backend data from a mobile sports education application.
  Keywords: Convolutional neural network; Physical education; Gamification; PD; User model; Learning partner matching.
  DOI: 10.1504/IJCSYSE.2027.10073462
   
  
• Personalised Teaching Mode of Music Education based on AI  
  by Yucong Song 
  Abstract: This paper presents the development and implementation of an AI-driven personalised teaching model for music education. The aim is to address the "one-size-fits-all" challenge and meet diverse student needs in music literacy, skill mastery, and creativity. We review the evolution of AI-based personalised teaching in music, examine key technologies, and analyse practical challenges. The personalised teaching model includes tailored curriculum content, flexible teaching methods, customised resources, real-time feedback mechanisms, and a diversified evaluation system. An innovative intelligent music teaching system, leveraging pre-trained language models, automates the acquisition and expression of music knowledge, providing personalised learning experiences. The results highlight the system's effectiveness in promoting technological innovation, modernising music education, enhancing student engagement, and fostering equitable, high-quality music education.
  Keywords: Artificial intelligence; Big models; Personalization; Music teaching; Teaching models.
  DOI: 10.1504/IJCSYSE.2027.10073835
   
  
• Using Big Data Analysis to Optimise English-Chinese Bilingual Classroom Teaching design  
  by Fenxiang Zhang 
  Abstract: With the rapid development of big data technology and its wide application in various fields, this study is devoted to exploring the role of big data in English-Chinese bilingual classroom teaching design. Through the comprehensive use of questionnaire survey and data analysis, the study reveals the importance of optimising teaching methods and improving student participation in improving learning results. This study found that interactive teaching methods and high student engagement are positively correlated with learning outcomes. In addition, big data analysis shows great potential in revealing educational trends and optimising teaching strategies. Based on these findings, this study suggests that educators adopt more interactive teaching methods in bilingual teaching and use big data tools to analyse student learning behaviours to improve teaching results. Future research could further explore the application of big data technologies in different educational Settings and the role of these technologies in educational innovation.
  Keywords: Big data; English-Chinese bilingual teaching; Teaching methods; Student engagement; Educational technology application.
  DOI: 10.1504/IJCSYSE.2028.10074052
   
  
• Enhancing User Experience with Prompt Recommendation Engine  
  by Aparna Chitta, Ajay Kumar Akasapu, H. Patra 
  Abstract: Prompt recommendation engines represent a novel approach to enhancing user experience by leveraging advanced language understanding to deliver personalized and relevant recommendations. These engines greatly boost engagement and satisfaction by creating concise prompts that address user interests and goals in domains such as e-commerce, search, and content discovery. This project uses prompt engineering and recommendation systems, thereby simplifying activities and improving interactions. Using Decision Tree Classifiers, Logistic Regression, and Support Vector Machines (SVMs), the system delivers personalized suggestions, with the SVM model having the highest accuracy and precision on a simulated dataset of text prompts across seven categories. These engines provide contextual cues in cases where users find roadblocks while looking for new information, easing the process. This strategy promises to transform user interactions with digital platforms by providing a personalized, seamless, and intuitive experience that boosts happiness and loyalty in a variety of disciplines.
  Keywords: Prompt Engineering; Recommendation Systems; Machine learning; Decision tree; Logistic Regression; Support Vector Machine.
  DOI: 10.1504/IJCSYSE.2028.10074714