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
   
  
• Risk Assessment of Network Public Opinion Information Circle based on CAFA-BP Algorithm  
  by Qianqian Zheng 
  Abstract: To address the issues of low coverage of influencing factors, low evaluation accuracy, and long response time in current risk assessment methods for network public opinion information circle dissemination, a risk assessment method of network public opinion information circle based on CAFA-BP algorithm is proposed. Optimise the LSTM model through attention mechanism, use the optimized LSTM model to predict the popularity of network public opinion, and determine the factors affecting communication risk based on the popularity of network public opinion. Using CAFA algorithm to optimise BP neural network, establish a risk assessment model based on CAFA-BP algorithm, and use this model to determine the risk value of network public opinion information circle propagation. The experimental results show that the maximum coverage rate of the influencing factors of the proposed method is 98.56%,the evaluation accuracy varies between 94.58% and 97.62%, and the response time varies between 1.23s and 1.69s.
  Keywords: CAFA-BP algorithm; Network public opinion information circle; Risk assessment; Popularity of network public opinion.
  DOI: 10.1504/IJIPT.2025.10072909
   
  
• Corporate Financial Risk Prediction Model Based on Deep Learning  
  by Fei Xue 
  Abstract: The correlation between financial success and corporate social responsibility (CSR) has been the subject of extensive research in recent years While prior studies have explored this relationship, objectively assessing the effectiveness of CSR programs has remained a considerable challenge However, advancements in research methodologies and the development of Environmental, Social, and Governance (ESG) measurement criteria have facilitated more reliable evaluations With the rapid advancement of artificial intelligence, and deep learning (DL) techniques have been increasingly applied across various domains The application of machine learning to ESG data analysis remains relatively limited Consequently, deep learning methodologies have proven to be practical, efficient, and effective approaches for predicting corporate financial performance based on ESG metrics Through risk management optimization, accuracy and recall rates have improved to 0 905 and 0 890, respectively The proposed risk prediction model achieves high accuracy rates of 90 5% and 92 4% in the training and test data sets, respectively.
  Keywords: Key performance indicator (KPI); Sustainable Development Goal (SDG); Return on equity (ROE); spiking neural networks (SNNs); artificial neural network (ANN); Deep learning (DL); machine learning (ML).
  DOI: 10.1504/IJIPT.2025.10072912
   
  
• Effective Information Classification Mining Method for IoT Big Data Based on Support Vector Machine  
  by Shumin Zhi 
  Abstract: The effective information classification mining of IoT big data is of great significance in enhancing data value, optimising resource allocation, and promoting technological innovation to solve the problems of low recall and precision, and long completion time in current methods. Research on effective information classification mining method for IoT big data based on support vector machine has been carried out. By optimising the selection of initial k values and initial clustering centre points, the improved K-means clustering algorithm is utilized to achieve big data collection in the Internet of Things. By predicting residuals for anomaly detection and removal of IoT data, the removed IoT big data is input into a fuzzy support vector machine to achieve information classification mining. The experimental results show that the average recall rate of the proposed method is 97.07%,the average precision rate is 96.72%, and the task completion time varies between 0.22s and 0.68s.
  Keywords: Support vector machine; IoT; Big data; Effective information; Classification mining; Improved K-means clustering algorithm.
  DOI: 10.1504/IJIPT.2025.10072914
   
  
• Timing optimisation method of traffic signal lights at congested intersections based on vehicle networking information collection  
  by Suli Zhang, Yulin Jiao, Xinhua Wang 
  Abstract: To reduce the average delay time of vehicles and improve the passing rate of vehicles, this paper designs a timing optimisation method for traffic signal lights at congested intersections based on vehicle networking information collection. Extracting data features through real-time collection of traffic flow data using vehicle networking technology to predict future traffic flow at specific times; the objective function is to minimize the average delay time of vehicles, and the average delay time of vehicles is taken as the fitness value of individual manta rays. The manta ray foraging optimisation algorithm is iteratively optimised, and the optimal timing scheme is obtained when the fitness value changes by less than 10-6.The experiment showed that after applying this method, the passing rate of vehicles ranged from 92.41% to 95.25%,and the maximum average delay time of vehicles was only 5 seconds, indicating that the method effectively achieved the design expectations.
  Keywords: Congested intersection; Traffic light; Timing for signal lights; Internet of Vehicles; Long short-term memory network; Optimisation algorithm for manta ray foraging; optimisation.
  DOI: 10.1504/IJIPT.2025.10073601
   
  
• A Travel Planning Method for Intelligent Networked Vehicles at Unsignalised Intersections based on Transformer Algorithm  
  by Miao Wang, Chen Sun 
  Abstract: In order to improve the success rate of conflict avoidance and the cumulative value return of routes, this paper designs a travel planning method for intelligent networked vehicles at unsignalized intersections based on Transformer algorithm. The intersection environment information is collected by multi-sensor, and the high-precision environment map is generated by filtering and calibration; A predictive model is built, using TCN to capture local spatiotemporal features, and Transformer analyzes global dependencies to accurately predict the driving intentions of other vehicles. Based on the prediction results, the safe travel path is generated through multi-modal intention fusion, space-time collaborative trajectory generation, safety boundary adjustment and real-time planning. Experiments show that the conflict avoidance success rate of the vehicle is always 1.00, and accumulated value return of the traveling path is closer to 1, indicating that the method realizes the safe driving of the vehicle in the unsignaled traffic environment.
  Keywords: Unsignalized intersection; TCN; Transformer; Intelligent networked vehicles; Travel planning.
  DOI: 10.1504/IJIPT.2026.10074058
   
  
• 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