IEEE Access最新文献

{"title":"ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images","authors":"Rui Xu;Zhenxing Zhuang;Renzhong Mao;Yihui Yang","doi":"10.1109/ACCESS.2025.3563459","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563459","url":null,"abstract":"Extracting road information from high-resolution remote sensing images has become a research hotspot in remote sensing image processing due to its cost-effectiveness and efficiency. Current road extraction methods generally face challenges such as large parameter sizes and limited accuracy when dealing with roads at different scales. To overcome these limitations, this study proposes a novel lightweight attention network model (ESLiteU2-Net) to improve both efficiency and accuracy of road extraction. Based on U2-Net, the proposed model reduces complexity by a channel reduction strategy and introduces an Efficient Spatial and Channel Attention Module (ESCA). This innovative design enables the model to better capture and reinforce road features across both spatial and channel dimensions, resulting in significant improvements in extraction accuracy and robustness while maintaining a lightweight structure. Experimental results demonstrate that ESLiteU2-Net outperforms existing methods on the CHN6-CUG and Massachusetts road datasets. Compared to U2-Net, the proposed model not only achieves superior accuracy but also reduces computational load and parameter number by 30.98% and 81.91%, respectively, achieving a balanced combination of lightweight design, efficiency, and accuracy for road extraction.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"71223-71239"},"PeriodicalIF":3.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model","authors":"Jingya Zheng;Gaofeng Tao;Shuxin Qin;Dan Wang;Zhongjun Ma","doi":"10.1109/ACCESS.2025.3563200","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563200","url":null,"abstract":"Storage resources are essential in heterogeneous multi-cloud environments. In response to the growing demand for efficient storage resource management (SRM) in these environments, this paper proposes an intent-based storage management (IBSM) system powered by a fine-tuned large language model (LLM). To overcome the limitations of existing methods, the IBSM system focuses on enhancing the controllability, completeness, and reliability of SRM in multi-cloud environments. Specifically, the IBSM system employs a dual-phase joint intent classification algorithm, which leverages a fine-tuned LLM to accurately identify user intents across diverse knowledge backgrounds. Additionally, the system constructs a collaborative intent decomposition method, which guarantees the integrity of intents. Furthermore, the system integrates an automated intent deployment mechanism that supports error recovery through checkpoints. Experimental results show that the system achieves a whole end-to-end (E2E) lifecycle for managing user intents. The E2E time is reduced by at least half compared to the manual approach, with an average of 50.14% dedicated to interactive tasks. Performance metrics for intent classification, including accuracy, precision, and recall, all exceed 90%. Moreover, the recovery time is reduced by an average of 30.6%. Therefore, the system provides a valuable solution for the autonomous management of multi-cloud resources.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72736-72753"},"PeriodicalIF":3.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975014","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lane-Keeping Assistance System Based on Model Predictive Control With Smooth Transitions Between Operational Modes","authors":"Younsung Hong;Jae-Sung Moon;Yunhyoung Hwang","doi":"10.1109/ACCESS.2025.3563626","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563626","url":null,"abstract":"The lane-keeping assistance system (LKAS) is one of the core functions of advanced driver assistance systems (ADAS) that prevents unintended lane departures. LKAS widely utilizes shared steering control, in which both the driver and the vehicle controller share lane-keeping control by integrating the driver into the control loop. The shared control approach can be formulated as a multi-objective optimization problem that optimizes between maintaining driver control and reducing driving burden, while preventing unintended lane departures. A model predictive control (MPC)-based method effectively can address multi-objective optimization problems in shared control. In addition, it provides the advantage of switching the operational mode by adjusting the weights in the cost function according to assessed risk. However, an abrupt transition between operational modes can cause unstable motion such as severe lateral jerk or hysteresis, resulting in driver discomfort. To address this issue, we propose a shared control framework that ensures smooth transitions between operational modes by applying a softly switched MPC method, in which the weights are modulated over the prediction horizon. Unlike existing approaches, the proposed method with the soft-switching scheme could enhance path-tracking accuracy, maintain steering stability, and suppress unstable lateral motion while improving driver comfort during switching between operational modes. Simulation experiments with various maneuvers and road curvatures demonstrated that the proposed framework could substantially suppress unstable lateral motion during mode transitions, even in severe cases, while complying with safety regulations.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73709-73721"},"PeriodicalIF":3.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974971","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Load Balancing and Alternative Path Selection in Self-Organized Networks: A Data Plane Approach","authors":"Gergely Sárközi;Péter Vörös","doi":"10.1109/ACCESS.2025.3563806","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563806","url":null,"abstract":"This paper presents a novel load balancing algorithm tailored for deeply programmable networks, offering a decentralized approach to optimizing packet forwarding and load distribution. Unlike conventional systems reliant on centralized controllers or manual configurations, this algorithm operates entirely within the data plane, leveraging controlled flooding to dynamically discover and reroute traffic based on real-time congestion data. By detecting latency spikes indicative of congestion, switches autonomously select alternative paths to maintain optimal traffic flow. Implemented in the P4 data plane programming language, the algorithm is rigorously evaluated against existing load balancing methods for self-organized networks. The results demonstrate significant reductions in data transmission times, improved path symmetry, and enhanced scalability under various network conditions, making it a robust solution for modern, self-organized, and high-performance networks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73540-73552"},"PeriodicalIF":3.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974967","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Early Warning Method Based on Blending of Deep Generative Model and Oversampling Model for Online Learning","authors":"Mingyan Zhang;Yiqing Wang;Jui-Long Hung;Jie Wang;Chao Duan","doi":"10.1109/ACCESS.2025.3563642","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563642","url":null,"abstract":"Early warning for learning performance requires to identify the maximum number of at-risk students as early as possible within a semester. However, educational data often suffer from the issue of data imbalance, making it challenging to simultaneously achieve both high precision (accurate identification) and high recall (comprehensive coverage) in at-risk student detection. Deep generative models and oversampling models are effective methods to solve data imbalance issues, which can improve classification performance. This paper proposes a method that combines the advantages of deep generative models and oversampling models to build a blending model for dealing with imbalanced educational data, which can effectively improve the precision, recall, F1-score and AUC for online learning early warning. First, we compare baseline models to select the best classifier, then choose the highest-precision deep generative model and the highest-recall oversampling model to construct blending models, which are shown to improve early warning prediction metrics. Finally, interpretable models are used to analyze differences in at-risk student prediction between the blending model, deep generative model, and oversampling model. The proposed models are validated on both extremely imbalanced datasets and new semester datasets. Results show that: (1) Compared to the baseline model, both the base learners built by the deep generative model and the oversampling model can improve the evaluation metrics of the model, the deep generative base learners achieve higher precision than the oversampling model, while the oversampling base learners achieve higher recall than the deep generative base learners. (2) The blending model composed of deep generative base learner and oversampling base learner can further improve the F1-score and AUC based on their individual strengths, the proposed blending model can also conduct effective early warning three units earlier than baseline models. (3) Compared to its base learners, blending model G-B-Blending changes the key variables for prediction, and the at-risk students identified by the blending model come from the union set of at-risk students identified by GAN+GB and B-SMOTE+GB individually. (4) The blending model proposed in this paper achieves better prediction results than the baseline on both extremely imbalanced datasets and new semesters datasets, it can identify more at-risk students more accurately at earlier units, allowing teachers to save more energy and time for teaching interventions. This research provides significant insights for dealing with imbalanced datasets by blending with deep generative model and oversampling model in education.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72248-72268"},"PeriodicalIF":3.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974956","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Improved Ensemble Method With Data Resampling for Credit Risk Prediction","authors":"Idowu Aruleba;Yanxia Sun","doi":"10.1109/ACCESS.2025.3563432","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563432","url":null,"abstract":"The increasing complexity and dynamic nature of financial data present significant challenges in accurately predicting credit risk, a critical task in the banking and finance sector. The application of machine learning (ML) in credit risk prediction has been hindered by the imbalanced nature of credit datasets. This study proposes an improved approach for predicting credit risk using a stacked ensemble method combined with a hybrid data resampling technique. The ensemble comprises random forests, logistic regression, and a convolutional neural network (CNN) as base learners, with the multilayer perceptron (MLP) serving as a meta-learner. To address the data imbalance, the Synthetic Minority Over-sampling Technique and Edited Nearest Neighbors (SMOTE-ENN) technique were applied. The proposed approach is benchmarked against other well-performing classifiers, including random forest, logistic regression, MLP, and CNN. The integration of hybrid data resampling with a robust stacking ensemble significantly enhanced credit risk prediction, with the proposed approach achieving sensitivity and specificity of 0.921 and 0.946 for the Australian dataset and 0.928 and 0.891 for the German dataset. Also, the stacked classifier achieved a sensitivity and specificity of 0.000 and 1.000 before data resampling for the Credit Risk Classification dataset with an accuracy of 0.7644. After data resampling, the accuracy, sensitivity, and specificity are 0.8056, 0.7989 and 0.8125, respectively. On the other hand, using the credit risk analysis for the extended banking loans dataset, the accuracy, sensitivity and specificity of the stacked classifier before data resampling are 0.8429, 0.6316, and 0.9216, respectively. After data resampling, the accuracy, sensitivity and specificity scores of the stacked classifier trained using the credit risk analysis for the extended banking loans dataset are 0.9632, 1.0000, and 0.9242, respectively. This shows that after data resampling, the performance of the stacked classifier trained using the credit risk analysis for the extended banking loans dataset outperformed other models.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"71275-71287"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973108","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive PPO With Multi-Armed Bandit Clipping and Meta-Control for Robust Power Grid Operation Under Adversarial Attacks","authors":"Mohamed Massaoudi;Katherine R. Davis","doi":"10.1109/ACCESS.2025.3563419","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563419","url":null,"abstract":"The seamless and resilient operation of power grids is crucial for ensuring a reliable electricity supply. However, maintaining high operational stability is increasingly challenging due to evolving grid complexities and potential adversarial threats. This paper proposes a novel composite enhanced proximal policy optimization (CePPO) algorithm to improve power grid operation under adversarial conditions. Specifically, our approach introduces three key innovations: 1) multi-armed bandit (MAB) mechanism for dynamic epsilon-clipping that adaptively adjusts exploration-exploitation trade-offs; 2) meta-controller framework that automatically tunes hyperparameters including the activation learning rate (ALR) penalties and exploration factors; and 3) integrated gradient-based optimization approach that combines policy gradients with environmental feedback. The effectiveness of the proposed model on the IEEE 14-bus system demonstrates that the CePPO achieves approximately 50% higher average rewards and 51% longer stability periods compared to standard PPO while reducing computational overhead by 35%. CePPO demonstrates superior performance under adversarial attacks compared to baseline approaches. The simulation results validate that CePPO’s adaptive parameter tuning and enhanced exploration strategies make it particularly well-suited for the dynamic nature of power grid control. To foster further research and reproducibility, the code is available upon request at <uri>https://github.com/Dr-Kate-Davis-s-Research-Team/DRL-CP.S</uri>","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73586-73602"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973609","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MonoDFM: Density Field Modeling-Based End-to-End Monocular 3D Object Detection","authors":"Gang Liu;Xinrui Huang;Xiaoxiao Xie","doi":"10.1109/ACCESS.2025.3563248","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563248","url":null,"abstract":"Monocular 3D object detection aims to infer the 3D properties of objects from a single RGB image. Existing methods primarily rely on planar features to estimate 3D information directly. However, the limited 3D information available in 2D images often results in suboptimal detection accuracy. To address this challenge, we propose MonoDFM, an end-to-end monocular 3D object detection method based on density field modeling. By modeling the density field from the features of a single image, MonoDFM enables a more accurate transition from 2D to 3D representations, improving 3D attribute prediction accuracy. Unlike traditional depth map methods, which are limited to visible regions, MonoDFM infers geometric information from occluded regions by predicting the scene’s density field. Moreover, compared with more complex approaches like Neural Radiance Fields (NeRF), MonoDFM provides a streamlined and efficient prediction process. Experiments conducted on the KITTI dataset show that MonoDFM achieves <inline-formula> <tex-math>$mathrm {AP_{3D}}$ </tex-math></inline-formula> of (25.13, 16.61, 13.82) and <inline-formula> <tex-math>$mathrm {AP_{BEV}}$ </tex-math></inline-formula> of (32.61, 22.14, 18.71) on the KITTI benchmark for the Car category under three difficulty settings (easy, moderate, and hard), achieving competitive performance. Ablation studies further validate the effectiveness of each component. As a result, MonoDFM offers an effective approach to monocular 3D object detection, demonstrating strong performance.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"74015-74031"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973614","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modified Swarm-Based Artificial Intelligence Optimization for Optimal Coordination of Directional Overcurrent Relays in Power System","authors":"Abdul Wadood;Hani Albalawi;Aadel Mohammed Alatwi;Herie Park","doi":"10.1109/ACCESS.2025.3563338","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563338","url":null,"abstract":"The coordination of directional overcurrent relays (DOCRs) plays a critical role in ensuring the reliability and robustness of modern electrical power protection systems. Achieving optimal relay coordination in multi-loop power networks is a complex optimization challenge requiring the minimization of relay operating times and achieve optimal tuning of time dial settings (TDS) and plug settings (PS) while considering the impact of DG integration. The proposed method employs a Quantum-Inspired Adaptive Walrus Optimization Algorithm (QIAWOA), a modified swarm-based artificial intelligence technique (AI) that incorporate rates quantum-inspired principles, such as adaptive quantum rotation gates, to enhance search dynamics and facilitate precise relay coordination. The performance of QIAWOA is validated using the IEEE 3, 8, and 15-bus systems, as well as the CEC 2020 benchmark suite, which includes multimodal and multi-objective optimization functions (MMOOF). QIAWOA demonstrates superior capabilities in identifying globally optimal solutions, significantly reducing relay operating times, and achieving robust coordination. Comprehensive statistical analyses, including empirical cumulative distribution functions (CDF), boxplots, histograms, probability plots, and quantile-quantile (QQ) plots, underscore the reliability and efficiency of the proposed method. Comparative evaluations with state-of-the-art nature-inspired techniques further highlight the enhanced performance of QIAWOA, establishing it as a powerful tool for improving the protection system performance in complex power networks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"71007-71026"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973606","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation of System-Level Reliability Functions for the Power Grid Using Probabilistic Modeling and Monte Carlo Simulation","authors":"Ayman Faza","doi":"10.1109/ACCESS.2025.3563427","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563427","url":null,"abstract":"Reliability Modeling for Power Systems is a very challenging task due to the high complexity of the interactions among its various components. In this paper, we develop a simple probabilistic method for modeling power system reliability based on the knowledge of the system size, transmission line capacities, and the failure rate type of the transmission lines in the system. Using Monte Carlo Simulation, we show that the probability distribution of the system failure rate is typically similar in shape to the failure distribution of the transmission lines in the system, with variations stemming from the system size, transmission line capacity, and the type of failure rate. Our method provides a very simple formula for describing system level reliability despite the high complexity of its interconnections, and provides a mechanism to develop similar functions for other complex systems, including different types of networks or critical infrastructures, and can pave the way towards better modeling for the more intelligent future grids.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"71388-71407"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973611","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}