International Journal of Computing Science and Mathematics (15 papers in press)

Regular Issues

• Research on High-Precision Insulator Classification Using an Improved Hybrid Attention Mechanism in the Context of Un-Manned Aerial Vehicles  
  by Qi Cao, Song Yang, Hao Lin Li, Xin Qiang Wu, Ming Liu, Zhijun Qin, Feng Wang 
  Abstract: With the increasing reliance on unmanned aerial vehicles (UAVs) for power transmission line inspections, there has been a growing need for more sophisticated image classification methods to analyse the vast number of images captured during these operations. Traditional methods often struggle with the accurate identification of critical components, such as insulators, which are essential for maintaining the integrity of power lines. In this study, we present an improved vision transformer (ViT) model specifically designed to classify insulator conditions into three categories: damaged, flashover, and normal. To facilitate this, we constructed a dedicated dataset featuring these three conditions of insulators. Our enhanced ViT model demonstrates superior performance compared to conventional deep learning models, offering higher accuracy and robustness in identifying insulator conditions. The experimental results highlight the models effectiveness, with significant improvements in classification accuracy, making it a valuable tool for enhancing the reliability and safety of power transmission line inspections.
  Keywords: Power Transmission Line Inspection; Insulator Condition Classification; Unmanned Aerial Vehicle (UAV); Deep Learning; Im-age Classification.
  DOI: 10.1504/IJCSM.2025.10073609
   
  
• Sports Pose Estimation based on Adaptive Complementary Data Fusion Algorithm  
  by Jinchi Yu, Xiaomin Gu 
  Abstract: Accurately estimating athlete pose is of great significance for improving training quality and preventing sports injuries. The current vision-based estimation methods are susceptible to environmental lighting interference, while inertial sensors suffer from cumulative errors. To optimize the accuracy and stability of athlete pose estimation, a motion pose estimation method based on adaptive complementary data fusion algorithm is proposed. A motion sensor data fusion algorithm based on Kalman filtering algorithm is designed to improve its accuracy. When the number of samples was 300, the pitch angle was 9After UKF filtering, the maximum Roll angle was 20 and the minimum Roll angle was 85. The Yaw angle error was reduced, with a maximum Yaw angle of 80 and a minimum Yaw angle of 100. The experimental data proves the effectiveness and superiority of the proposed algorithm.
  Keywords: Kalman filtering algorithm; pose estimation; athletic sports; adaptive algorithm; sensor data fusion.
  DOI: 10.1504/IJCSM.2025.10073775
   
  
• Bidirectional Optimised Auction Model for Carbon Emission Rights with Incremental Reserve Price Strategy  
  by Zenghua Du, Hongren Yan, Sheng Yang, ZhiGuo Hu 
  Abstract: Carbon emission trading has become a widely adopted and effective strategy for mitigating greenhouse gas emissions. Among the various trading mechanisms, auction-based models have demonstrated superior efficiency in allocating emission allowances. However, existing studies primarily emphasise revenue maximisation, often overlooking the critical role of the sellers reserve price. This paper argues that incorporating a reserve price not only safeguards the sellers interests but also incentivises buyers to engage in energy conservation and emission reduction efforts. We propose a novel multi-stage auction model that jointly optimises the revenues of both sellers and buyers across multiple bidding rounds, incorporating seller-defined, non-decreasing reserve price functions. Theoretical analysis confirms the correctness and convergence of the model, and illustrative examples are provided to demonstrate its practical applicability. Compared to existing approaches, our model offers a more realistic and balanced framework by explicitly considering the impact of dynamic reserve pricing on the benefits of both parties, thereby aligning more closely with the operational needs of carbon auction markets.
  Keywords: Auction Model; Carbon Emission Right; Reserve Price; Maximum Revenue.
  DOI: 10.1504/IJCSM.2025.10073855
   
  
• Simulation Optimisation of Maicai Delivery Location using the Elbow Method and K-Means Clustering Algorithm  
  by Yonghua Lu, Bingda Zhang, Yuting Shen, Zixia Chen 
  Abstract: This study proposes an innovative integration of the elbow method and the K-means clustering algorithm to optimise delivery centre locations for Maicai. Based on 55 demand sites, a model is constructed to analyse geographic positions and order volumes. The elbow method is first applied to determine the optimal number of clusters (k), followed by K-means clustering to iteratively optimize delivery centre locations. Python is used to generate a k-S.S.E relationship curve and identify the inflection point automatically. This approach provides data-driven support for determining the optimal number of clusters and uses K-means to perform spatial clustering of demand points. Empirical results demonstrate that the hybrid method effectively reduces logistics costs and enhances delivery efficiency, demonstrating operational efficiency improvements for real-world delivery operations.
  Keywords: delivery-center location; elbow method; K-means clustering; logistics optimization; delivery efficiency.
  DOI: 10.1504/IJCSM.2025.10074316
   
  
• Learning-Assisted Empirical Mode Decomposition Algorithm for Pre-stack Seismic Wave Impedance Prediction  
  by Shucheng Sun, Bo Tang, Xuesong Yan 
  Abstract: Among numerous oil and gas exploration technologies, pre-stack seismic inversion technology based on reservoir elastic parameter information that can reflect more stratigraphic characteristics has become a popular technology in seismic inversion due to its ability to improve the accuracy of exploration.This paper proposes a learning-assisted empirical mode decomposition algorithm This algorithm addresses the problems of over envelope and under envelope in empirical mode decomposition algorithms, using segmented cubic Hermite interpolation algorithm instead of cubic spline interpolation, and using feature scale extension to reduce endpoint influence. To eliminate invalid components, correlation coefficients are used to remove some invalid components and reduce modal aliasing. In order to verify the performance of the proposed algorithm, traditional data processing methods and improved methods were compared with other algorithms to verify the improvement of wave impedance parameter prediction accuracy of the proposed algorithm.
  Keywords: Pre-stack seismic inversion; Elastic parameters; Empirical Mode Decomposition; Convolutional neural network.
  DOI: 10.1504/IJCSM.2025.10074359
   
  
• Global-Local Temporal Attention Network for short-Term Solar Irradiance Prediction  
  by Jian Wang 
  Abstract: The intermittent nature of solar radiation presents challenges to power system stability due to unpredictable fluctuations in energy generation. To address this, we propose a solar irradiance prediction method based on the Global-Local Temporal Attention Network (GLTAN). The GLTAN comprises three key components: the Global-Local Feature Extraction (GLFE) module, the Temporal Attention Mechanism (TAM), and the Gated Recurrent Unit (GRU). The GLFE module uses a dual-layer Transformer and Temporal Convolutional Network (TCN) to extract both global and local features, capturing short-term and long-term trends. The TAM selectively highlights relevant information, while the GRU captures short-term dependencies. Experimental results for four different prediction time steps show that GLTAN outperforms the other models, with an average of 7.3% improvement in R2 over nine prediction steps.
  Keywords: Solar irradiance; short-term prediction; global-local feature extraction; self-attention mechanism.
  DOI: 10.1504/IJCSM.2025.10074450
   
  
• Adaptative Strategies for Solving Partial Differential Equations by Kansa's Method  
  by Selma Bouzit 
  Abstract: This work presents an innovative and efficient meshless method for solving high-dimensional partial differential equations (PDEs). By utilising generalised multiquadric radial basis functions (RBFs) with an exponent , the method incorporates various shape parameter c selection strategies to enhance numerical accuracy. Three approaches: optimal, trigonometric, and random for  and c are analysed for their performance across different problems. The method's mathematical foundation is rigorously studied, and extensive numerical experiments confirm its accuracy and robustness in solving linear and nonlinear PDEs across various dimensions. The results demonstrate its potential as a reliable and versatile tool for high-dimensional PDE applications.
  Keywords: Partial differential equations; Linear problems; Non-linear problems; Radial basis functions; Kansa method; Shape parameter.
  DOI: 10.1504/IJCSM.2025.10074451
   
  
• Consideration of Energy Market for High Proportion of Wind Power with Trading Mechanism for the Frequency Regulation Ancillary Services Market  
  by YUwei Wang, Jing Wang, Baoqiang Li, Yong Wang 
  Abstract: As the penetration of wind and other clean energy sources increases, their uncertainty exacerbates the imbalance between supply and demand for frequency regulation resources. Traditional clearing mechanisms for energy and frequency regulation face issues such as capacity crowding and excessive reliance on thermal power flexibility. Focusing on wind-dominated power markets, this paper compares the PJM and CAISO market mechanisms in the United States and integrates current renewable energy integration and trading practices. A frequency regulation market clearing model is proposed in which generators incorporate opportunity costs into their offers, and two clearing frameworks joint and sequential are developed for energy and frequency regulation markets. Case studies based on the proposed model analyse the effects of different renewable penetration levels on market efficiency. Results show that under high penetration, the joint clearing model significantly reduces total system cost and wind curtailment through global resource optimisation.
  Keywords: High Percentage of Wind Power; Electric Energy Market; Frequency Regulation Market; Clearing Models.
  DOI: 10.1504/IJCSM.2025.10074474
   
  
• An Efficient Hash-Based Assessment and Recovery Algorithm for Distributed Healthcare Systems  
  by Ramzi A. Haraty, Mohammad Jaber 
  Abstract: Advancements in healthcare information technology have improved data sharing and patient care but also introduced cybersecurity risks. This study proposes a distributed algorithm to assess damage from cyberattacks and accelerate database recovery. The algorithm influences hash tables for efficient identification and retrieval of affected transactions, minimising execution time and resource consumption. A checkpoint mechanism further optimises performance by discarding outdated logs. Comparative analysis demonstrates the algorithm's effectiveness in mitigating attack impact and enhancing healthcare system resilience. By integrating hash tables for rapid data retrieval, this approach offers a robust solution to safeguard critical medical data.
  Keywords: Damage Assessment; Database Recovery; Distributed Databases; Information Warfare; and Healthcare Systems.
  DOI: 10.1504/IJCSM.2025.10074482
   
  
• News recommendation optimisation path based on improved GAT algorithm  
  by Kunlong Yang, Minjing Wang 
  Abstract: To solve the problem of recommending massive news information mentioned above, a semantic representation model based on news text information fusion is proposed. The innovation lies in the use of capsule networks and Transformers for feature extraction and fusion, while proposing a perceptual model for graphic attention networks to enhance the capture of relevant information. In the accuracy recall analysis, the research model achieved an accuracy of 0.962 in sports news scenarios, which is superior to the other two models. In the comparison of recommendation accuracy, the model showed the best performance with recommendation accuracy of 0.915 and 0.961 on the Yahoo and MIND datasets, respectively. It can be seen that the research model meets the requirements of news and user development. The research content will provide important technical references for the effective dissemination of news and the improvement of recommendation techniques.
  Keywords: GAT; news recommendations; capsule network; transformer; perception model.
  DOI: 10.1504/IJCSM.2025.10073091
   
  
• A faster algorithm for calculating evaluation function in Hex game  
  by Ze Liu, Yi Wang, Bin Wang, Puyuan Du, Yungang Zhu 
  Abstract: Queenbee is an exceptional evaluation function in search-based AI algorithms for Hex. It assesses each empty cell on the board by calculating a unique metric known as 'Two-distance', traditionally determined via a breadth-first search with O(n2) time complexity. In this paper, we introduce the Contour Line Algorithm (CLA), which reduces the time complexity to O(n) without increasing space complexity. CLA computes the Two-distance for each cell layer by layer, treating connected blocks of cells with identical Two-distance values as contour lines. Experimental results show that CLA significantly outperforms the traditional approach.
  Keywords: Hex game; evaluation function; computer gaming; contour line algorithm.
  DOI: 10.1504/IJCSM.2025.10074181
   
  
• Linear polynomial algebra migration system for program equivalence and approximate optimisation  
  by Weiwen Ge, Weidong Tang, Meiling Liu 
  Abstract: Program structure simplification constitutes a critical research domain in software engineering. With increasing system complexity, traditional simplification approaches remain predominantly confined to deterministic equivalence verification, lacking substantial investigation into approximate equivalence, error quantification, and control mechanisms. This paper develops a novel concept of common algebraic set bisimulation equivalence by integrating Wu's characteristic series within a linear polynomial algebraic migration system framework. To address non-deterministic equivalence problems, this work introduces novel least squares solution metrics and singular value thresholding control mechanisms. These innovations establish an approximate bisimulation equivalence theory that quantifies program behavior differences while maintaining controllable error bounds. Consequently, approximately equivalent systems can replace the original complex systems, thereby simplifying program architecture. Experimental validation using a concurrent communication program demonstrates the efficacy of our proposed methodology in program optimisation.
  Keywords: Wu's characteristic series; linear polynomial algebra migration system; least squares solution; singular value thresholding; approximate bisimulation equivalence.
  DOI: 10.1504/IJCSM.2025.10073023
   
  
• REC-YoloPose: a lightweight model for enhancing human pose estimation performance in multi-scale and complex scenes  
  by Weize Chen, Chenyang Shi, Donglin Zhu, Changjun Zhou 
  Abstract: Human pose estimation is a computer vision research area, but it faces challenges in balancing model complexity and accuracy. To address this problem, this study proposes an improved model named REC-YoloPose, based on Yolov8sPose. Firstly, the contextual guidance (CG block) is employed to replace traditional convolution, and efficient local attention (ELA) is introduced into the backbone, enhancing the model's feature extraction capability. Secondly, inspired by Repvit, the original Cross-Stage Partial fusion module (C2f) is improved, striking a balance between model parameters and recognition accuracy. Experimental results demonstrate that the proposed model achieves AP50 scores of 93.1% and 87.0% on Leeds sports pose (LSP) dataset and common objects in context (COCO) dataset respectively. Compared with other mainstream pose estimation algorithms, this model reduces computational parameters by 16.9% to 80.5% while maintaining high detection accuracy. Finally, REC-YoloPose is applied to human posture classification, showcasing its practical value in real-world tasks.
  Keywords: human pose estimation; context guided block; ELA; efficient local attention; cross stage partial fusion.
  DOI: 10.1504/IJCSM.2025.10073104
   
  
• Research on optical music recognition based on improved CRNN network and its application in piano teaching  
  by Jianing Wang 
  Abstract: The traditional optical music recognition method has the problem of low recognition accuracy and efficiency. An optical music recognition method based on convolutional recurrent neural network (CRNN) is proposed. Firstly, residual depthwise separable convolution is introduced into convolutional layer of CRNN network. Then, after convolution operation, squeeze-excitation module in attention mechanism is introduced. Finally, parameters of cross entropy function are adjusted at transcription layer. The results reveal that error rate of note recognition and sequence recognition in optical music is 1.26% and 7.31% respectively, which is significantly lower than those of CRNN model and SE-bi-directional long short-term memory (SE-BiLSTM) model. This model can improve training speed, and its recognition time is only 6.44 s, which is 7.89 s and 14.65 s lower than that of other two methods, respectively. It shows that recognition efficiency of the proposed model is significantly improved, which can meet the actual teaching needs of piano classrooms.
  Keywords: CRNN network; optical music recognition; SE module; note feature extraction; piano teaching.
  DOI: 10.1504/IJCSM.2025.10073780
   
  
• Construction of practical teaching data classification model based on ROF-SSA-LGBM and its application in physical education teaching and management  
  by Xinjiao Zhang 
  Abstract: Under the background of informatisation, to better assist the management of practical teaching, a data classification model based on ROF-ISSA-LGBM is proposed. Firstly, rotation forest algorithm (ROF) is used to screen importance features of practical teaching dataset. Then, improved sparrow search algorithm (ISSA) is adopted to optimise hyperparameters of lightweight gradient boosting machine (LGBM). Finally, ISSA-LGBM is used as the classifier and applied to the classification of practical teaching datasets. The results reveal that on Haberman and Iris datasets with smaller sample sizes, average accuracy, macro average, and micro average of the constructed model reach 80.96%, 95.38% and 95.44%, respectively, its performance is better than that of commonly used classification models, which means the constructed model has high classification accuracy. Therefore, the constructed model can be used for deep mining of potential information in the dataset of physical education practice teaching data, and shows high classification accuracy.
  Keywords: rotating forest algorithm; physical education practice teaching; SSA; sparrow search algorithm; LGBM; lightweight gradient boosting machine; combination model; macro average.
  DOI: 10.1504/IJCSM.2025.10073777