IEEE Access最新文献

{"title":"Corrections to “A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction”","authors":"Saba Taheri Kadkhoda;Babak Amiri","doi":"10.1109/ACCESS.2025.3557462","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3557462","url":null,"abstract":"Presents corrections to the paper, (Corrections to “A Hybrid Network Analysis and Machine Learning Model for Enhanced Financial Distress Prediction”).","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"61122-61122"},"PeriodicalIF":3.4,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10962182","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817785","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":"Corrections to “A Comprehensive Review and Analysis of the Allocation of Electric Vehicle Charging Stations in Distribution Networks”","authors":"T. Yuvaraj;K. R. Devabalaji;J. Anish Kumar;Sudhakar Babu Thanikanti;Nnamdi I. Nwulu","doi":"10.1109/ACCESS.2025.3554026","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3554026","url":null,"abstract":"","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"59749-59749"},"PeriodicalIF":3.4,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10960389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817897","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":"Corrections to “YOLO-DLHS-P: A Lightweight Behavior Recognition Algorithm for Captive Pigs”","authors":"Changhua Zhong;Hao Wu;Junzhuo Jiang;Chaowen Zheng;Hong Song","doi":"10.1109/ACCESS.2025.3552810","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3552810","url":null,"abstract":"Presents corrections to the paper, (Corrections to “YOLO-DLHS-P: A Lightweight Behavior Recognition Algorithm for Captive Pigs”).","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"58442-58442"},"PeriodicalIF":3.4,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10954785","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143801042","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":"A Unified Approach to Video Anomaly Detection: Advancements in Feature Extraction, Weak Supervision, and Strategies for Class Imbalance","authors":"Rui Z. Barbosa;Hugo S. Oliveira","doi":"10.1109/ACCESS.2025.3557948","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3557948","url":null,"abstract":"This paper explores advancements in Video Anomaly Detection (VAD), combining theoretical insights with practical solutions to address model limitations. Through comprehensive experimental analysis, the study examines the role of feature representations, sampling strategies, and curriculum learning in enhancing VAD performance. Key findings include the impact of class imbalance on the Cross-Modal Awareness-Local Arousal (CMALA) architecture and the effectiveness of techniques like pseudo-curriculum learning in mitigating noisy classes, such as “Car Accident.” Novel strategies like the Sample-Batch Selection (SBS) dynamic segment selection and pre-trained image-text models, including Contrastive Language-Image Pre-training (CLIP) and ViTamin encoder, significantly improve anomaly detection. The research underscores the potential of multimodal VAD, highlighting the integration of audio and visual modalities and the development of multimodal fusion techniques. To support this evolution, the study proposes a Unified WorkStation 4 VAD (UWS4VAD) to streamline research workflows and introduces a new VAD benchmark incorporating multimodal data and textual information. The work envisions enhanced anomaly interpretation and performance by leveraging joint representation learning and Large Language Models (LLMs). The findings set the stage for future advancements, advocating for large-scale pre-training on audio-visual datasets and shifting toward a more integrated, multimodal approach to VADs. Source code of the project available at <uri>https://github.com/zuble/uws4vad</uri>","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"60969-60986"},"PeriodicalIF":3.4,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949172","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817972","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":"Power Theft Detection in Smart Grids Using Quantum Machine Learning","authors":"Konstantinos Blazakis;Nikolaos Schetakis;Mahmoud M. Badr;Davit Aghamalyan;Konstantinos Stavrakakis;Georgios Stavrakakis","doi":"10.1109/ACCESS.2025.3558143","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3558143","url":null,"abstract":"Electricity theft can lead to enormous economic losses and cause operational and security problems for electricity networks and utilities. Most current research has focused on electricity theft detection in the consumption sector. However, the high penetration rate of distributed generation (DG) can lead to an increase in power theft attacks in this sector via smart meter manipulation. This study is an extension of prior works focused on electricity theft detection in the consumption and generation domains of a smart grid environment with DG. This study proposes a novel electricity theft detection framework based on quantum machine learning (QML). The elegant field of QML has been used to demonstrate that data classification becomes more efficient in higher-dimensional spaces. An extensive numerical study was conducted to determine the type of QML architecture that can perform well and efficiently in electricity theft detection cases. The technique presented here has not yet been extensively studied in the domain of energy theft detection. Extensive experiments were conducted to assess this approach, and an accuracy of 0.87 was achieved with respect to the classical consumption domain, whereas an accuracy of 0.977 was achieved with respect to the net metering domain.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"61511-61525"},"PeriodicalIF":3.4,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817875","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":"Iterative Assessment of Edge Criticality: Efficiency Enhancement or Hidden Insufficiency Detection","authors":"Vasily Lubashevskiy;Hamza Ejjbiri;Ihor Lubashevsky","doi":"10.1109/ACCESS.2025.3557852","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3557852","url":null,"abstract":"The assessment of edge criticality ranking in complex networks is a challenging issue in network science and has numerous applications, including network decomposition and, conversely, enhancing the resilience and redundancy of complex systems. Two main approaches are commonly used to rank edges based on their importance for maintaining network connectivity. The first is the Static approach, which relies on a single evaluation of topological features. The second is the Optimization-based approach, which treats network decomposition as an integral process and optimizes the edge sequence for network decomposition using genetic-like algorithms. While the Static approach is computationally efficient, the Optimization-based approach potentially yields the best decomposition pattern. In the present work, we propose the Iterative approach, which bridges the gap between these two methods. The Iterative approach involves a loop of identifying the most critical edge using selected ranking algorithms, removing it from the network, and then re-assessing edge criticality based on the modified network topology. As a result, the ranking of edge criticality depends not only on the initial topology of the network but also on its continuous modifications caused by edge removal. To evaluate the efficiency of the Iterative approach, we analyze the decomposition of sixteen well-known real-world benchmark networks using seven widely recognized edge ranking algorithms. The results demonstrate, first, that the Iterative approach can achieve a tenfold increase in the efficiency of network decomposition. Second, the analysis reveals hidden inner insufficiency in edge ranking for some algorithms, as evidenced by the fact that algorithm iterations can reduce decomposition efficiency. Additionally, we discuss the time complexity of the Iterative approach and strategies for its reduction. We also outline a potential framework for combining the Static and Iterative approaches during the network decomposition process to further enhance its efficiency.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"60889-60902"},"PeriodicalIF":3.4,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949212","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817965","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":"Optimizing Fairness and Spectral Efficiency With Shapley-Based User Prioritization in Semantic Communication","authors":"Moirangthem Tiken Singh;Adnan Arif;Rabinder Kumar Prasad;Bikramjit Choudhury;Chandan Kalita;Sikdar Md. S. Askari","doi":"10.1109/ACCESS.2025.3558107","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3558107","url":null,"abstract":"Efficient and fair resource allocation is a critical challenge in modern semantic communication systems, particularly in scenarios where numerous users compete for limited resources. Traditional methods, such as the Hungarian algorithm and greedy allocation, primarily focus on maximizing spectral efficiency, often neglecting fairness in resource distribution. This paper introduces a Shapley value-based framework that integrates Semantic Spectral Efficiency (S-SE) with fairness-driven prioritization. By leveraging Shapley values, the framework quantifies each user’s marginal contribution to overall system performance, enabling equitable and context-aware resource allocation. Semantic similarity is embedded directly into the allocation process, allowing the proposed method to intelligently manage resources based on channel conditions and the semantic relevance of transmitted information. Experimental evaluations demonstrate the framework’s effectiveness, achieving significant improvements in fairness, as measured by Jain’s Fairness Index, without compromising spectral efficiency. The Shapley-based approach outperforms established methods, including the Hungarian algorithm, reinforcement learning algorithms like Deep Q-Network (DQN) and Proximal Policy Optimization (PPO), as well as conventional 4G and 5G resource allocation strategies. Notably, as the number of channels increases, S-SE stabilizes while fairness continues to improve, approaching optimal levels in diverse system configurations. Although the Shapley value calculation introduces a moderate increase in computational cost, this trade-off is justified by the robust balance achieved between fairness, efficiency, and overall system performance. These results highlight the potential of the proposed framework to advance next-generation wireless communication systems by prioritizing semantic relevance and equitable resource allocation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"61299-61311"},"PeriodicalIF":3.4,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949192","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817873","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":"On BESS Capacity Optimization of Hybrid Coal-Fired Generator and BESS Power Station for Secondary Frequency Regulation","authors":"Xinsong Zhang;Ziyun Ma;Beiping Gu;Lurui Fang;Xiuyong Yu","doi":"10.1109/ACCESS.2025.3557853","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3557853","url":null,"abstract":"Integrating battery energy storage systems (BESS) into a coal-fired generator can enhance power systems’ secondary frequency regulation capability. To this end, this paper proposes a policy to coordinate the BESS and the coal-fired generator to meet the automatic generation control (AGC) requirements and subsequently investigates the optimal BESS capacity to maximize the net profit gained from the frequency regulation. Firstly, probability characteristics of AGC instruction duration period, interval period, regulation rate, and regulation direction are investigated according to the real AGC datalog. The AGC regulation direction would change randomly. Directly switching the BESS between charging and discharging to match the requirement would significantly deplete the lifetime of the battery. Therefore, this paper divides the BESS into two groups, which will be controlled stay in charging and discharging states to respectively respond to the AGC requirement of “up” and “down”. To obtain a cost-effective BESS investment, this paper develops a new sizing method, which optimizes the BESS capacity by simulating the operation of the hybrid coal-fired generator and BESS power station (HCGBPS) over an example day. Finally, the case studies justified the developed sizing method could make satisfying BESS investment decisions to ensure a maximum net profit in operation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"60833-60845"},"PeriodicalIF":3.4,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949211","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817971","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 Enhanced Path Loss Model for Maritime Communication Channels","authors":"Chongquan Wang;Shengming Jiang","doi":"10.1109/ACCESS.2025.3557824","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3557824","url":null,"abstract":"This study proposes a new ocean propagation loss model, the curved ground loss (CGL) model, to improve the existing models by considering the effects of sea surface roughness, earth curvature, and sea wave height on signal fading at the reflection point. The CGL model integrates a variety of loss factors, including air absorption loss, which has a significant impact on high-frequency and long-distance communications, reflection loss (including diffuse reflection effect and shadow fading), and diffraction loss caused by earth curvature. By comparing with measurement data, the accuracy of the CGL model is verified, achieving an RMSE of approximately 4–5 dB, with the best agreement with the measurement data for four cases: high frequencies, low antennas, the reflection effect and the distance exceeding 60% of the radius of the first Fresnel Zone (<inline-formula> <tex-math>$D_{06}$ </tex-math></inline-formula>).","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"60814-60821"},"PeriodicalIF":3.4,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949170","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817982","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":"A Novel Security Threat Model for Automated AI Accelerator Generation Platforms","authors":"Chao Guo;Youhua Shi","doi":"10.1109/ACCESS.2025.3558072","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3558072","url":null,"abstract":"In recent years, the design of Artificial Intelligence (AI) accelerators has gradually shifted from focusing solely on standalone accelerator hardware to considering the entire system, giving rise to a new AI accelerator design paradigm that emphasizes full-stack integration. Systems designed based on this paradigm offer a user-friendly, end-to-end solution for deploying pre-trained models. While previous studies have identified vulnerabilities in individual hardware components or models, the security of this paradigm has not yet been thoroughly evaluated. This work, from an attacker’s perspective, proposes a threat model based on this paradigm and reveals the potential security vulnerabilities of systems by embedding malicious code in the design flow, highlighting the necessity of protection to address this security gap. In exploration and generation, it maliciously leverages the exploration unit to identify sensitive parameters in the model’s intermediate layers and insert hardware Trojan (HT) into the accelerator. In execution, malicious information is concealed within the control instructions, triggering the HT. Experimental results demonstrate that the proposed method, which manipulates sensitive parameters in a few selected kernels across the middle convolutional layers, successfully misclassifies input images into specified categories with high misclassification rates across various models: 97.3% in YOLOv8 by modifying only three parameters per layer in three layers, 99.2% in ResNet-18 by altering four parameters per layer in three layers and 98.1% for VGG-16 by changing seven parameters per layer in four layers. Additionally, the area overhead introduced by the proposed HT occupies no more than 0.39% of the total design while maintaining near-original performance as in uncompromised designs, which clearly illustrates the concealment of the proposed security threat.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"61237-61249"},"PeriodicalIF":3.4,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949221","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817974","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}