Jiahui Wei , Zhongwen Zou , Wenjie Lai , Junliang Du , Jiaxue Zhao , Ziji Liu , Shengzhe Wang
{"title":"RGB-Thermal cameras calibration based on Maximum Index Map","authors":"Jiahui Wei , Zhongwen Zou , Wenjie Lai , Junliang Du , Jiaxue Zhao , Ziji Liu , Shengzhe Wang","doi":"10.1016/j.compeleceng.2025.110234","DOIUrl":"10.1016/j.compeleceng.2025.110234","url":null,"abstract":"<div><div>Calibration across multiple sensors is crucial in computer vision tasks, such as image registration, 3D reconstruction, and target tracking. RGB-Thermal (RGB-T) cameras, widely used as a multi-sensor combination, traditionally depend on manual calibration methods to determine extrinsic parameters. However, this manual process is intricate and lacks the capability for online calibration during use. To overcome these challenges, an online calibration algorithm for RGB-T camera extrinsic parameters is proposed. The algorithm first addresses modal differences by matching feature point pairs using the Maximum Index Map (MIM) feature. These matched features are then used to calculate the extrinsic parameters through homography and epipolar constraints between images. Additionally, a convenient intrinsic calibration method is introduced, one that does not rely on extrinsic infrared light sources, thereby overcoming the limitations of standard calibration boards, which are often unsuitable for RGB-T cameras. Experimental results demonstrate that the proposed online extrinsic calibration algorithm significantly simplifies the calibration process compared to traditional methods, achieving accurate calibration with only a pair of images. The method achieves an average reprojection error of 0.677 pixels for RGB images and 0.635 pixels for thermal images, highlighting its precision. The method’s effectiveness is further validated by the precision in RGB-T image registration.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110234"},"PeriodicalIF":4.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiale Xiao, Lei Xu, Changyun Li, Ling Tang, Guogang Gao
{"title":"MFYOLO: Improved UAV lightweighting algorithm for wind turbine blade surface visibility damage detection","authors":"Jiale Xiao, Lei Xu, Changyun Li, Ling Tang, Guogang Gao","doi":"10.1016/j.compeleceng.2025.110225","DOIUrl":"10.1016/j.compeleceng.2025.110225","url":null,"abstract":"<div><div>Ensuring the structural integrity of wind turbine blades in alignment with dual-carbon objectives is crucial for optimizing wind power generation. To address the challenge of identifying small and complex defect features while maintaining a lightweight and efficient algorithm, this study introduces an innovative image input methodology. This approach combines the original image, a super-resolution enhanced image, and a defect-magnified image, resulting in significant improvements in average accuracies (mAP50 and mAP50–95) of 94.7 % and 83.3 %, respectively. The proposed lightweight algorithm, MFYOLO, employs multilayer aggregated depth-separable convolutions for deep feature extraction, alongside spatial pyramid pooling to capture multi-scale details and reduce feature map dimensionality. Dynamic convolution and a generalized reverse bottleneck structure adjust the size and sampling strategy of the convolution kernel, while self-attention mechanisms and convolution module grouping effectively reduce the computational burden. Knowledge distillation further enhances MFYOLO's performance without increasing the parameter count. Compared to the benchmark, memory usage (RAM), computational demand (GFLOPs), and parameter count (Params) are reduced by 48.2 %, 47 %, and 48.9 %, respectively, while maintaining stable mAP50 and significantly improving mAP50–95 and accuracy. The method achieves 156 frames per second (FPS), with robust performance validated on multiple datasets.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110225"},"PeriodicalIF":4.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ironmaking process modeling uncertainty quantification via conformal prediction based on random vector functional link networks","authors":"Ping Zhou , Chaoyao Wen , Peng Zhao , Mingjie Li","doi":"10.1016/j.compeleceng.2025.110247","DOIUrl":"10.1016/j.compeleceng.2025.110247","url":null,"abstract":"<div><div>For real-world industrial system modeling, dynamic stochastic errors inevitably exist in data-driven deterministic predictions (i.e., point predictions). The uncertainty of such prediction results directly affects various prediction-based operations for work condition identification and production decision-making. Therefore, a novel interval prediction method quantifying multi-output uncertainty is proposed by combining conformal prediction with random vector functional link networks (RVFLNs), which has fast learning speed and high accuracy performance. The proposed algorithm is used for the reliable prediction of molten iron quality in blast furnace ironmaking process. Firstly, to address the issue that shallow learning models have limited expression capabilities to describe complex nonlinear relationships, the dynamic attention mechanism and semi-supervised autoencoder are utilized to reveal and represent the correlations between different input variables and multi-output variables. Subsequently, the Elastic Net regularization technique is adopted to improve the multicollinearity and overfitting problems of traditional RVFLNs. Further, considering the deterioration of prediction accuracy and credibility caused by uncertain system dynamics, an Empirical Copula function-based Copula prediction uncertainty quantification method is introduced to realize multi-output variables reliable prediction with a given confidence level. Finally, actual blast furnace industrial data is applied to demonstrate the validity, utility, and sophistication of model.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110247"},"PeriodicalIF":4.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Gene-related multi-network collaborative deep feature learning for predicting miRNA-disease associations","authors":"Pengli Lu, Xu Cao","doi":"10.1016/j.compeleceng.2025.110242","DOIUrl":"10.1016/j.compeleceng.2025.110242","url":null,"abstract":"<div><div>A growing number of experiments have shown that microRNAs (miRNAs) play a key role in regulating gene expression, and their aberrant expression may lead to the development of specific diseases. Therefore, accurate identification of the associations between miRNAs and diseases is crucial for the prevention, diagnosis and treatment of miRNA-related diseases. However, existing models have limitations in accurately capturing biological information and comprehensively extracting features. To address this problem, we propose gene-related multi-network collaborative deep feature learning for predicting miRNA-disease associations (MNFLMDA). First, we constructed three heterogeneous networks, miRNA-gene, disease-gene and miRNA-disease, and mined the potential information of the heterogeneous networks using Auto-Encoder and Graph Attention Networks. Subsequently, this potential information was fused to form the final features. Finally, these features were used to predict the associations between miRNAs and diseases. To validate the effectiveness of the model, we conducted extensive experiments on the Human miRNA Disease Database and compared it with eight of the most representative models over the past two years, and the results showed that MNFLMDA exhibits excellent performance. In addition, case studies of breast tumors, colorectal tumors and hepatocellular carcinoma were conducted to further validate the predictive performance of MNFLMDA.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110242"},"PeriodicalIF":4.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multiclass vulnerability and clone detection in Ethereum smart contracts using Block-wise Abstract Syntax Tree based Federated Graph Neural Networks","authors":"Shruti Sharma, Ankur Ratmele, Abhay Deep Seth","doi":"10.1016/j.compeleceng.2025.110220","DOIUrl":"10.1016/j.compeleceng.2025.110220","url":null,"abstract":"<div><div>Smart contracts on blockchain networks autonomously execute applications based on predefined conditions, making their security-critical due to the potential for significant financial losses from vulnerabilities. Current vulnerability detection algorithms commonly rely on expert-defined rules, which are prone to errors and insufficient for identifying complex vulnerability patterns. Given the immutability of smart contracts post-deployment, ensuring security before deployment is essential. This research presents Block-wise Abstract Syntax Tree based Federated Graph Neural Networks (BAST-FeGNN), a novel approach combining block-wise abstract syntax tree and Federated Graph Neural Networks (FeGNN) to detect code clones and multiclass vulnerabilities in Ethereum smart contracts. The BAST-FeGNN method operates in three stages: it first extracts security-related patterns from the base code using an abstract syntax tree; then, it constructs and normalizes a contract graph using FeGNN to capture critical nodes, analyze data and control flows. This integration of graph-based feature extraction with pattern matching allows precise detection of vulnerabilities like access control issues, reentrancy, and unchecked calls, as well as identifying code clones. Finally, the method pools these features for comprehensive vulnerability detection. BAST-FeGNN significantly enhances vulnerability detection accuracy and scalability, outperforming existing models with an accuracy of 95.35%, recall of 95.58%, F1-score of 95.80%, and precision of 96.10%, making it a robust solution for securing blockchain applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110220"},"PeriodicalIF":4.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143609294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MSDAHNet: A multi-scale dual attention hybrid convolution network for breast tumor segmentation","authors":"Xuelian Yang , Yuanjun Wang , Jinli Zhao , Li Sui","doi":"10.1016/j.compeleceng.2025.110199","DOIUrl":"10.1016/j.compeleceng.2025.110199","url":null,"abstract":"<div><div>Accurate breast tumor segmentation is crucial for physicians in breast cancer diagnosis and clinical analysis. To address challenges such as the diversity in tumor size and shape, as well as the indistinct boundaries in breast tumor segmentation, we propose a multi-scale dual attention hybrid convolution network (MSDAHNet). MSDAHNet incorporates a residual dual channel attention module in the encoder and decoder, allowing it to capture essential image features more effectively. In the down-sampling of encoding, both max-pooling and average-pooling are utilized to minimize the loss of fine features. Besides, the network introduces a multi-scale feature pyramid aggregation module and a multi-scale hybrid convolution module to facilitate the integration of important feature mappings and enhance the tumor regions. We conduct experiments using four breast imaging datasets. Specifically, Dice scores of MSDAHNet on BUSBRA, BUET_BUSD, private hospital, and BreaDM datasets are 0.906, 0.842, 0.853, and 0.832, respectively, and Iou scores are 0.841, 0.768, 0.780, and 0.745 for each dataset respectively. The experimental results demonstrate that MSDAHNet outperforms comparing to existing state-of-the-art methods, showing good potential in breast tumor segmentation.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110199"},"PeriodicalIF":4.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143609295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Distributed energy procurement with renewable energy sources in a radial distribution system","authors":"Souvik Roy, Rhythm Singh","doi":"10.1016/j.compeleceng.2025.110268","DOIUrl":"10.1016/j.compeleceng.2025.110268","url":null,"abstract":"<div><div>The integration of renewable-based distributed generation (DG) in distribution systems can modernize the grid, delivering cleaner, cost-effective, and resilient power while deferring expensive upgrades. This study explores renewable DG integration in a 51-bus radial system to reduce energy procurement costs and emissions while improving voltage and power loss profiles. Optimal DG siting and sizing are achieved using a voltage stability index (VSI) and enhanced particle swarm optimization (PSO). A novel energy coverage ratio (ECR) index ensures efficient DG selection. Additionally, levelized cost of energy (LCOE) and solar-based time-of-use (ToU) pricing factors are calculated for DG energy pricing. The energy procurement problem is solved for four cases under two scenarios using an alternating current optimal power flow (ACOPF) method with MATLAB-based MATPOWER. Results show a 2.41 % cost reduction, 4.77 % emission abatement, and 10.49 % energy loss reduction when 49.52 % of the annual renewable DG generation is procured.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110268"},"PeriodicalIF":4.0,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xinzhe Xie , Buyu Guo , Peiliang Li , Shuangyan He , Sangjun Zhou
{"title":"Multi-focus image fusion with visual state space model and dual adversarial learning","authors":"Xinzhe Xie , Buyu Guo , Peiliang Li , Shuangyan He , Sangjun Zhou","doi":"10.1016/j.compeleceng.2025.110238","DOIUrl":"10.1016/j.compeleceng.2025.110238","url":null,"abstract":"<div><div>In recent years, the two-stage multi-focus image fusion (MFF) method, which utilizes neural networks to first generate decision maps and then calculate the fused image, has witnessed significant advancements. However, after supervised training, many networks become overly reliant on semantic information, making it challenging to discern whether homogeneous regions and flat regions are in focus or not, as these regions lack distinct blur cues. To alleviate this issue, this paper proposes a multi-focus image fusion network named BridgeMFF by applying a visual state space model and developing a general fine-tuning technique named BridgeTune, which bridges the semantic and texture gap via dual adversarial learning. By fine-tuning the entire network in an adversarial manner, decision maps are generated to synthesize clear and blurred images with probability density distributions closely approximating real ones, thereby implicitly learning local spatial patterns and statistical properties of pixel values. Extensive experiments demonstrate that the proposed BridgeMFF achieves superior fusion quality, especially in challenging homogeneous regions. Moreover, BridgeMFF has the smallest model size (0.05M) and fastest processing speed (0.09s per image pair), enabling real-time fusion applications. The codes are available at <span><span>https://github.com/Xinzhe99/BridgeMFF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110238"},"PeriodicalIF":4.0,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mostefa Kara , Mohammad Hammoudeh , Muhamad Felemban , Konstantinos Karampidis
{"title":"An encrypted and signed plaintext symmetric cryptosystem","authors":"Mostefa Kara , Mohammad Hammoudeh , Muhamad Felemban , Konstantinos Karampidis","doi":"10.1016/j.compeleceng.2025.110244","DOIUrl":"10.1016/j.compeleceng.2025.110244","url":null,"abstract":"<div><div>Traditionally, encryption and digital signatures are handled as separate processes, resulting in distinct ciphertexts. This article investigates a novel approach to integrating encryption and digital signatures within a symmetric cryptosystem to meet the dual requirements of confidentiality, integrity, and authenticity in secure communications. Our research proposes a method that combines encryption and signature functionality within a probabilistic symmetric cryptosystem, reducing operational complexity and minimizing overhead. We introduce a protocol that employs a shared secret key for both encrypting plaintext and generating a verifiable signature within a single ciphertext. By modifying the encryption process, we enable certain variables to function as an implicit signature. The security and performance implications of this protocol are rigorously evaluated through theoretical analysis and experimental testing. Results show that the proposed scheme maintains robust security while significantly improving message-handling efficiency, it achieves four layers of security against quantum computer attacks and five against classical computers, compared to only one, two, or three layers in previous techniques in literature. To the best of our knowledge, this is the first protocol to merge encryption and digital signature creation into a single process and ciphertext, offering an enhanced solution for secure communications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110244"},"PeriodicalIF":4.0,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimal power flow solutions for normal and critical loading scenarios using hybrid Rao-2 sine cosine algorithm","authors":"Udit Mittal , Uma Nangia , Narender Kumar Jain , Saket Gupta","doi":"10.1016/j.compeleceng.2025.110230","DOIUrl":"10.1016/j.compeleceng.2025.110230","url":null,"abstract":"<div><div>This study explores integrating a novel Hybrid Rao-2 Sine Cosine Algorithm (HRSCA) into power systems to address optimal power flow (OPF) challenges, particularly under high loading and contingency scenarios. HRSCA combines the Sine-Cosine Algorithm's exploratory capabilities with the Rao-2 algorithm's exploitative strengths, enhancing convergence speed and solution quality. It balances exploration and exploitation, ensuring diverse, optimal solutions that meet OPF constraints without added complexity. Rigorous testing on IEEE 30-bus and 118-bus systems demonstrates its robust performance and superiority over contemporary algorithms in standard OPF studies and scenarios like load growth and generator outages. HRSCA effectively lowers fuel costs and emissions, improves voltage stability, minimizes voltage deviations, and enhances load margin stability under operational stressors like faults. For example, in generator outage scenarios on the IEEE 30-bus system at a loading factor of 1.0932 p.u., it achieved a fuel cost of 1,021.6998 $/h, reflecting a marginal yet noteworthy 0.03 % improvement over the previously reported 1,022.0078 $/h. It also reduced power loss to 9.4336 MW, a notable 3.46 % improvement from 9.772 MW, with emission costs as low as 0.3726 ton/h and 0.3802 ton/h, respectively. For the IEEE 118-bus system, HRSCA minimized fuel costs to 129,088.63 $/h, a 1.62 % improvement over the base case of 131,220.52 $/h, outperforming many recent algorithms. These results highlight HRSCA's potential to enhance efficiency, stability, security, and environmental performance, even under critical conditions.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110230"},"PeriodicalIF":4.0,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}