International Journal of Internet Protocol Technology (10 papers in press)

Regular Issues

• Faultload Sequences for the MQTT Protocol Services  
  by Amina Jandoubi, M.Taha Bennani, Olfa Mosbahi 
  Abstract: We have proposed preliminary results of a new approach to extract the sequences of events that model the fault injection times at the MQTT messaging protocol level to assess their reliability. After targeting publish service, we got seven possible scenarios to put the system in a faulty state. We introduced new algorithms to: (1) extract send and receive events from CFGs, (2) identify send/receive pairs, (3) time stamp the events using a vector clock, (4) filter sending events, and (5) generate alternative send sequences. In this paper, we extended the initial results by applying the approach to the services provided by the Publisher, the Subscriber, and the MQTT Broker, which increased the number of scenarios up to seventeen fault injection sequences. This contribution is the first step in formalising the description of all possible attacks on the MQTT protocol, which is crucial to reinforce the reliability of its services.
  Keywords: MQTT; Internet of things; Fault injection; Control-Flow Graphs.
  DOI: 10.1504/IJIPT.2026.10072721
   
  
• Optimising Student Performance Prediction Using DTC Enhanced with WOA and ECPO  
  by Lijuan Gao, Caiyan Chen 
  Abstract: To enhance academic outcomes in today's competitive educational environment, institutions must proactively predict student performance, classify students based on skill levels, and provide early guidance. Forecasting student success using past performance can help reduce failure rates and implement targeted interventions. Educational data exploration employs analytical techniques to identify trends in teacher and student data, offering valuable insights for planning and forecasting. This study combined two advanced optimization techniques: the Waldrus Optimization Algorithm (WOA) and Electric Charged Particles Optimization (ECPO), with Decision Tree Classification (DTC) to predict student outcomes. Standard performance metrics, including precision, accuracy, recall, and F1-score, were used for evaluation. Results indicated that both optimisers significantly improved the model's effectiveness. DTC+ECPO excelled in the "Acceptable" performance category, while DTC+WOA was highly effective in identifying "Poor" performance students. These findings validate WOA and ECPO as robust tools for predictive analytics and early academic intervention.
  Keywords: Student success; DTC; Walrus Optimization Algorithm; Electric Charged Particles Optimization.
  DOI: 10.1504/IJIPT.2026.10074169
   
  
• Task Scheduling Optimisation for Wireless Sensor Modules in Cloud-Based Systems  
  by Ananya A, Santhosh Krishna B. V, MURUGAVEL A, Sivakumaran C 
  Abstract: Scheduling algorithms demonstrate the critical function they play in the cloud data centres in determining a potential timetable for the work. Since the goal is to achieve the shortest total execution time, existing research has demonstrated that the job scheduling issue is NP-Complete. we consider the issue of minimising the total layover time by scheduling a set of l jobs with a set of 'G' groupings to a set of m clouds. Here, we describe a pair-based work scheduling method based on the well-known optimisation process known as the Hungarian algorithm for cloud data centres. Two performance indicators, specifically makespan and averaged cloud utilisation, are used to assess their performances via simulation. The method will decrease task waiting times and increase resource efficiency as a consequence. The results of the experiment demonstrate that the suggested technique enhances resource consumption while decreasing task execution times.
  Keywords: Task management; the Hungarian method; and normalisation all relate to the cloud. make span Cloud use; the node weight method; the Hopfield neural network; and Jflap.
  DOI: 10.1504/IJIPT.2026.10074204
   
  
• Intelligent Retrieval Method for Legal Information Based on Semantic Knowledge Graph  
  by Yuxia Gao 
  Abstract: In the digital media era, information overload complicates effective data filtering, causing cognitive fatigue and reduced decision-making efficiency. To address this, we propose a personalised recommendation method for online digital media based on user interests. Our approach constructs a user interest model using term frequency statistics and co-occurrence-based tag filtering, dynamically updated via a forgetting factor. We design an enhanced list-wise recommendation model using deep neural networks, which processes user and message features into vector inputs. The model incorporates positional encoding and multi-head attention mechanisms, along with point-wise feedforward networks and residual connections, ultimately predicting click-through rates and optimising ranking through a Softmax output layer. Experimental results indicate that our method achieves a stable MRR between 0.516 and 0.599 (fluctuation: 0.083) and maintains Precision above 95%, effectively mitigating the cognitive burden of information overload and delivering key content more accurately to target users.
  Keywords: Legal information; Intelligent retrieval; Semantic features; Knowledge graph; lagrange algorithm.
  DOI: 10.1504/IJIPT.2026.10074413
   
  
• Personalised Recommendation Method for Network Digital Media Information based on User Interests  
  by Yaoyi Xu 
  Abstract: In order to place the correct recommendations at the forefront and improve the accuracy of media information recommendations, a personalised recommendation method for network digital media information based on user interests is proposed. Construct a user interest model by integrating word frequency statistics and co-occurrence relationship filtering labels, and then introduce forgetting factors to dynamically update the user interest model. A personalised recommendation method for enhanced lists based on deep neural networks was designed, which generates vector inputs through user feature transformation and message feature extraction. Introducing position encoding and multi head attention mechanism, combined with point by point feedforward neural network and residual connection, and finally achieving accurate click probability prediction and message sorting optimisation through Softmax output layer. The experimental results show that the MRR value of our method is stable between 0.516-0.599 (with a fluctuation of only 0.083), and the recommended accuracy remains above 95% effectively mitigating the cognitive burden of information overload and delivering key content more accurately to target users.
  Keywords: User interests; Network digital media; Media messages; Personalized recommendations.
  DOI: 10.1504/IJIPT.2026.10074415
   
  
• AI.Driven Personalised Curriculum Framework for Enhancing Cross. Cultural Learning: A Case Study in Chinese Cultural Education at Guilin Tourism University  
  by Yun Tang, Chaohua Su 
  Abstract: With the accelerated pace of globalization and the rapid advancement of artificial intelligence (AI) technology, international student education is confronted with unprecedented opportunities and challenges. Existing international education systems often suffer from a lack of personalization and static content delivery, failing to fully address the diverse and personalized learning needs of international students. Drawing on the Constructivist Learning Theory and Intercultural Communication Competence Model, and integrating the application scenarios of AI technology, this study proposes a comprehensive AI-driven personalized curriculum framework for enhancing cross- cultural learning, taking Chinese cultural education for international students at Guilin Tourism University as a case study. The framework, structured around four key componentsgoal setting content creation teaching implementation evaluation feedback utilises AI to dynamically tailor learning paths, generate multimodal resources and provide real time feedback. Implementation at Guilin Tourism University has shown promising results, including increased student engagement, satisfaction and skill acquisition in Chinese cultural understanding. This framework not only improves the learning outcomes of Chinese culture among international students but also offers insights for broader applications in international education and policy-making, highlighting the potential of AI to revolutionise cross-cultural education.
  Keywords: AI-assisted teaching; international student education; Chinese culture; curriculum system; cross-cultural communication.
  DOI: 10.1504/IJIPT.2026.10074642
   
  
• Time Series Prediction of Stock Market Movements by Utilising the BRO-SVR Hybrid Model: A Case Study of the Shanghai Stock Exchange  
  by Weishuang Xu, Daming Li, Siqi Hao 
  Abstract: Predicting future stock prices is challenging due to numerous uncontrollable factors. However, data-driven methods have enabled more accurate forecasts despite inherent uncertainties. Traditionally, such forecasts relied on technical and fundamental indicators. With advancements in Machine Learning (ML), prediction accuracy and accessibility have significantly improved. This study presents a novel approach that integrates the Battle Royale Optimisation (BRO) algorithm with an enhanced support vector regression model to predict stock prices. Applied to data from the Shanghai Stock Exchange, the proposed model demonstrated high prediction accuracy. It consistently outperformed existing methods, significantly improving time series forecasting of stock values. High R
  Keywords: Stock Price Prediction; Support Vector Regression (SVR); Battle Royale Optimization (BRO); Shanghai Stock Exchange (SSE); Machine Learning (ML); Metaheuristic Algorithms; Time Series Forecasting.
  DOI: 10.1504/IJIPT.2026.10074741
   
  
• RSSCE: A SAM-Based MapReduce Framework for Mining Uncertain Big Data in Cloud Environments  
  by Huiguo Dong, Jing Zhang, Qinlu He 
  Abstract: The exponential growth of data generation encompassing text, images and videos through social media and digital platforms has introduced significant challenges in extracting meaningful insights. While big data presents numerous opportunities, leveraging it effectively for business and decision-making remains a key focus of information technology. Data retrieval aims to transform vast, unstructured data sets into valuable information, with particular emphasis on identifying frequent patterns repeated items, substructures or sequences that meet user-defined thresholds. Owing to the immense data volume, users often operate on specific subsets, thereby limiting the search space. To address this, a technique utilising the Search Area Minimisation (SAM) approach integrates user-defined constraints to narrow the search field and highlight relevant patterns. Experimental results across deterministic and uncertain data sets. This proposed approach provides a scalable and reliable solution for frequent pattern mining in big data environments, enabling focused and effective analysis based on user preferences and uncertainty management.
  Keywords: Big Data; Uncertain Data; Frequent Pattern Extraction; Search Space Reduction; User Constraints; MapReduce Framework; SAM Technique; Data Analysis; Non-Deterministic Databases.
  DOI: 10.1504/IJIPT.2026.10074763
   
  
• Mitigating Subjective Bias in Football Player Valuation Using Hybrid ANFIS with Bio Inspired Optimisation Algorithms  
  by Pengyu Qi, Xia Liu, Tao Yan, Xin Zhou 
  Abstract: Football is one of the most extensively followed sports worldwide, with athletes from numerous countries participating in regional and international tournaments, demonstrating both skill and dedication. The market value of footballers serves as a critical metric for evaluating their actual worth and overall quality. To estimate the market value of football players, an Adaptive Neuro-Fuzzy Inference System (ANFIS) was employed. Additionally, two advanced metaheuristic algorithms the Weevil Damage Optimisation Algorithm (WDOA) and the Wild Geese Optimisation Algorithm (WGOA) were integrated to enhance the predictive accuracy of the ANFIS model. These integrations resulted in two hybrid models: ANFIS + WDOA (ANWD) and ANFIS + WGOA (ANWG). Among the models tested, ANWD exhibited the highest performance, achieving an R
  Keywords: Artificial intelligence; Machine learning; Market value; Football; Adaptive neuro-fuzzy inference system; Weevil damage optimization algorithm; Wild geese optimization algorithm.
  DOI: 10.1504/IJIPT.2026.10074764
   
  
• Predictive Modelling of Financial Crisis in the Environmental Protection Industry Using PCA-Enhanced BP Neural Network and SVM Approaches  
  by Yupeng Li, Ke Sun 
  Abstract: Corporate financial crises are complex and unpredictable, making the establishment of effective early warning mechanisms essential for minimising potential risks. This study assesses the forecasting capabilities of backpropagation neural networks (BPNNs) and support vector machines (SVMs) in predicting financial crises within enterprises. Using data from 92 listed companies in the environmental protection industry, a comprehensive early warning indicator system was created, incorporating 16 financial indicators and 2 non-financial indicators. Principal Component Analysis (PCA) was employed to reduce the dimensionality of financial indicators, extracting six main components. MATLAB-based training and testing revealed that BPNN achieved a precision of 98.39% in the training set, outperforming SVM by 5.17%, and a precision of 93.33% in the test set, surpassing SVM by 7.68%. These results highlight the superior performance of BPNN in early warning systems, offering a robust tool for enhancing financial risk management and decision-making.
  Keywords: corporate financial crisis early warning; principal component analysis; support vector machine; environmental protection industry; back propagation neural network.
  DOI: 10.1504/IJIPT.2026.10074918