International Journal of Internet Protocol Technology (8 papers in press)

Regular Issues

• Data Mining Technology for Machinery Equipment and Information Networks  
  by Li Yang, Yongqiang Wang, Jielong Geng 
  Abstract: In order to predict the Rate of penetration (ROP) during drilling, a new data mining technology for drilling ROP prediction is proposed. The weight of the ROP influencing factors determined by the Analytic hierarchy process (AHP) and the original data are used as the input information, after neural network training and iteration, the drilled ROP model is determined, finally, the model is used to simulate and predict the ROP to be drilled in the same area. Simulation results show, that the Analytic hierarchy process-back propagation (AHP-BP) combined model established by the feedforward neural network principle can improve the iterative convergence speed and the reliability of the training results to a certain extent. Experimental results show that the predicted value of drilling speed is basically close to the actual value, the relative error is controlled within 10%, and the prediction effect is good with an accuracy of 98%.
  Keywords: Rate of penetration (ROP) prediction; data mining; Analytic hierarchy process; neural network; Analytic hierarchy process-Back Propagation (AHP-BP); Neural network.
  DOI: 10.1504/IJIPT.2025.10071284
   
  
• An Innovative Method for Highly Accurate Stock Price Forecasting: a Case Study on HSI  
  by Shuyu Hu, Ming Huang 
  Abstract: Volatility in the stock market is attributable to many interrelated factors operating in the background. Changes in the unemployment rate, global economic data, immigration policies, public health conditions and monetary policies that impact nations are all potential causes. All participants pursue a comprehensive stock market assessment to increase profits and decrease risks. The globe is searching for a precise and trustworthy forecasting model encompassing the highly variable and nonlinear market behaviour inside a comprehensive framework. This study predicts the close price of the Hang Seng Index (HSI) the following day using a hybrid model called Long Short-Term Memory (LSTM) with a combination of the artificial bee colony. The proposed model achieved optimal outcomes by utilising conventional factors, including a Root Mean Square Error (RMSE) of 180.21, a Mean Squared Error (MSE) of 32474, a coefficient of determination of 0.9941 and a Mean Absolute Error (MAE) of 135.61.
  Keywords: Stock exchange; financial market; Stock future price; long short-term memory; Artificial bee colony.
  DOI: 10.1504/IJIPT.2025.10071457
   
  
• Intelligent Robot Path Planning Based on Multimodal Deep Learning Algorithm  
  by Linyan Pan 
  Abstract: In order to overcome the problems of poor performance, low obstacle avoidance success rate, and long time in traditional intelligent robot path planning methods, this paper proposes an intelligent robot path planning method based on multimodal deep learning algorithm. By using depth cameras, LiDAR, and IMU to collect multimodal data, and utilising multimodal deep learning algorithms to determine the characteristics of the collected signal and image data, intelligent robot obstacle target detection can be achieved. By combining the gravity and repulsion functions of the artificial potential field method to improve the RRT Connect algorithm, a smooth path trajectory is obtained by smoothing the inflection point of the path through a cubic B-spline curve. The experimental results show that the proposed method has high smoothness and low complexity of intelligent robot paths, shorter paths, an average obstacle avoidance success rate of 97.08%, and an average path planning time of 74.25 ms.
  Keywords: Multimodal deep learning algorithm; Intelligent robots; Path planning; Multimodal data; Improved RRT-Connect algorithm.
  DOI: 10.1504/IJIPT.2025.10071615
   
  
• Network Big Data Association Recommendation Method based on Modified Entropy and Improved FCM Algorithm  
  by Xiaomin Liu 
  Abstract: To overcome the problems of low accuracy, low recall, and long generation time of recommendation results in traditional recommendation methods, a network big data association recommendation method based on modified entropy and improved FCM algorithm is proposed. Calculate the information entropy of network data and correct it. Use the corrected entropy to perform dimensionality reduction on the data. Calculate the abnormal factor value of the network data after dimensionality reduction to detect and remove abnormal data. Use an improved FCM algorithm to cluster the data after removing anomalies. Build a CLUPCDR model through data augmentation module, user feature extraction module, and mapping header module, and use this model to implement network big data association recommendation. The experimental results show that the maximum accuracy of the proposed method is 98.74%, the maximum recall is 99.12%, and the recommended result generation time varies between 0.19s and 0.57s
  Keywords: Corrected entropy; Improved FCM algorithm; Network big data; Association recommendation; Abnormal factor value; CLUPCDR model.
  DOI: 10.1504/IJIPT.2025.10071756
   
  
• Enhanced Congestion Control in Transmission Control Protocol using Harmonic Red Panda Optimisation for Heterogeneous Networks  
  by Maya Diwakar, Anita Yadav 
  Abstract: Transmission Control Protocol (TCP) plays a crucial role in daily activities, from accessing emails to internet browsing. To ensure consistent and secure data delivery while minimizing data loss, innovative mechanisms are essential. While TCP performs well in conventional environments with traditional congestion control (CC) approaches, achieving high utilization, stability, and fairness in heterogeneous networks remains a challenge. This research introduces the Harmonic Red Panda Optimization (HRPO) method for CC in TCP, a novel approach combining Harmonic analysis with Red Panda Optimisation (RPO). Initially, TCP system model is simulated and then, a designed TCP algorithm performs the following steps. Firstly, Congestion Window (CWND) is initialised and next, estimation of bandwidth (BW) is carried out. Thereafter, computation of CC factor is done and finally, convergence factor is estimated. The estimation of convergence factor is performed by HRPO. Experimental results demonstrate that HRPO achieves significant improvements, including a maximal goodput of 1951.352 Mbps, throughput of 1587.167 Mbps and a Signal to Interference Noise Ratio (SINR) of 39.595dB. These results highlight the superiority of HRPO in delivering higher performance and stability compared to existing CC methods, particularly in heterogeneous network environments.
  Keywords: Transmission Control Protocol (TCP); Congestion Control (CC); Congestion Window (CWND); Harmonic analysis; Red Panda Optimization (RPO).
  DOI: 10.1504/IJIPT.2025.10071759
   
  
• Enhancing Electric Power Communication Network Resilience via Disintegration Strategy based on Adaptive Tabu Search under Cascading Failure  
  by Danni Liu, WanChang Jiang, Zeng Dou, Shengda Wang, Haoqin Qin, Yutong Li, Song Zhang 
  Abstract: To enhance resilience of electric power communication network against attacks, an optimal spatial complex network disintegration strategy is proposed. Firstly, a spatial complex network model is developed, incorporating topology and geographic data, and a disintegrating circle is introduced to simulate attacks and damage. Secondly, node traffic and capacity are calculated, aiding in construction of the cascading failure process. Finally, an optimization model is constructed for the disintegration strategy. And a self-adaptive heuristic algorithm using tabu search is designed to identify the optimal disintegration strategy under the case of cascade failure. Simulations experiments are conducted on two real-world electric power communication networks. Compared with the other three methods, the critical attack strength, the robustness metric and the largest connected component are reduced by an average of 22 %, 38 %, and 36 %, respectively. Our strategy can find the optimal disintegration region in the network to disintegrate the network more efficiently.
  Keywords: spatial complex network; disintegration strategy; cascading failure; disintegrating circle.
  DOI: 10.1504/IJIPT.2025.10071806
   
  
• Improving Android Malware Detection: Hybrid Models Integrating SGDC with SHO and GNDO Optimisation  
  by Peng Chen, Yan HE 
  Abstract: Android app development is evolving rapidly, but Android malware is dangerous. Many approaches for malware detection have been proposed and researched in studies, with one such effective tool being machine learning (ML). In this study, Stochastic Gradient Descent Classification (SGDC) was utilised for Android malware prediction, supplemented with Sea Horse Optimization (SHO) and Generalized Normal Distribution Optimization (GNDO) for increased predictive performance. Hybrid models were developed by combining these optimisation algorithms: SGDC with SHO (SGSH) and SGDC with GNDO (SGGN). SGSH achieved a testing accuracy of 0.990, with SGGN following closely with 0.972 accuracy. For precision, SGSH again performed best at 0.991, with SGDC reporting a minimum of 0.952.
  Keywords: Android malware; Machine learning; Stochastic gradient descent classification; Sea horse optimisation; Generalized normal distribution optimisation.
  DOI: 10.1504/IJIPT.2025.10072082
   
  
• Real time Monitoring for University Network Public Opinion Information Based on Improved Deep Learning  
  by Jinhao Guo 
  Abstract: To improve the coverage of public opinion concepts and the accuracy of monitoring public opinion popularity, this paper designs a real time monitoring method for university network public opinion information based on improved deep learning. Normalise the online public opinion data of universities and use an improved stacked denoising autoencoder to extract features from public opinion information. By introducing sparsity constraints, the model avoids learning redundant features and improves the generalisation ability of feature representation. Based on the SEIR model and propagation threshold calculation, a dynamic monitoring model for online public opinion in universities was constructed to predict the development trend of public opinion in real time and effectively warn of the malignant evolution of public opinion. The experimental results show that the concept coverage of this method can reach a maximum of 0.991, and the accuracy of public opinion heat monitoring can reach a maximum of 0.95.
  Keywords: University management; Online public opinion information; Public opinion monitoring; Stacked denoising autoencoder; Feature extraction; Sparsity constraint; SEIR model.
  DOI: 10.1504/IJIPT.2025.10072117