IEEE Access最新文献

{"title":"Data Reliability Testing Framework for Biometric Datasets Using Synthetic Iris and Fingerprint Images Generated via Deep Generative Models","authors":"Hyoungrae Kim;Hakil Kim","doi":"10.1109/ACCESS.2025.3604894","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3604894","url":null,"abstract":"This paper presents a comprehensive data reliability testing framework for evaluating synthetic biometric data, addressing privacy concerns in fingerprint and iris recognition systems. This unified and modality-independent methodology establishes six quantitative metrics: randomness, quality similarity, attribute similarity, non-duplication, ID-preservation, and geometric diversity. The framework is implemented through a novel RD-Net architecture consisting of a Random Network for privacy protection and a Deterministic Network for maintaining essential biometric characteristics. Experiments using public datasets (FVC 2002, IITDelhi-Iris, and CASIA-Iris-V4) demonstrate that synthetic samples maintain high dissimilarity from source datasets while preserving their structural properties. The synthetic biometric data generated through the proposed Random Network and Deterministic Network architectures are evaluated using the data reliability testing framework, confirming distribution similarity with real data across all proposed metrics and achieving scores over 80. This approach offers a method for generating and evaluating synthetic biometric data that balances privacy protection with functional validity in biometric system development and testing.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"155084-155095"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146748","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021228","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":"Guidelines and Feasibility of Base Station Deployment for Hyperloop Communications","authors":"J. Kim;H. Kim","doi":"10.1109/ACCESS.2025.3603965","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3603965","url":null,"abstract":"This paper presents an analytical framework for base station (BS) deployment in Hyperloop communication systems. Recognizing the challenges of the systems, the study proposes three guidelines for BS deployment: 1) synchronized pod passage at BS locations, 2) exclusive spectrum access for each pod, and 3) symmetric deployment around the tube mid-point. The framework classifies all possible BS deployments and derives explicit existence conditions based on key system parameters: tube length as well as pod’s acceleration, maximum speed, and departure interval. The investigation reveals that only specific pod acceleration completion scenarios, where pods finish accelerating within the coverage of certain BSs, permit the guidelines to be satisfied, while other cases are shown to be infeasible due to conflicts with the guidelines. This framework enables a Hyperloop communication system designer to determine the location of BSs required for a set of given system parameters. Furthermore, the results demonstrate that BS deployments determined based on 30-second departure interval remain feasible for any departure interval which is an integer multiple of 30 seconds. This ensures scalability and robustness for real-world scheduling.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154069-154079"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146545","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021275","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":"ST-DGCN: A Novel Spatial-Temporal Dynamic Graph Convolutional Network for Cardiovascular Diseases Diagnosis","authors":"Qi Xu;Yi Xia","doi":"10.1109/ACCESS.2025.3605241","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605241","url":null,"abstract":"Recently, Deep Learning (DL) technology has made significant progress in the field of automatic diagnosis of cardiovascular diseases (CVDs) based on electrocardiograms (ECGs). Multi-lead ECG signals are physiological signals obtained through a series of lead systems based on potential differences between electrodes placed on the limbs and chest. However, most DL models treat them as one-dimensional signals distributed in Euclidean space, often focusing only on features along the temporal dimension and neglecting the spatial relationships between different leads. Different studies indicate that these spatial relationships are physiologically significant for the diagnosis of CVDs, as they represent the activity of different regions of the heart. Given the advantages of Graph Convolutional Networks (GCNs) in analyzing non-Euclidean data, this study proposes a novel method for CVD diagnosis. The method begins by segmenting ECG signals into multiple single-lead segments and converting them into the nodes of a graph. Subsequently, these nodes are interconnected through spatial-temporal connections based on their relationships of physiological structures. The proposed model utilizes a dynamic graph convolutional network to capture the spatial-temporal features of the ECG signals and employs hierarchical pooling techniques to mitigate issues of oversmoothing and overfitting. Compared to other state-of-the-art models (SOTAs), this model achieved at least a 6.5% and 9.3% increase in F1 scores on the Chapman and PTB-XL databases, respectively, such significant performance advantages highlight the effectiveness and reliability of the model in classifying ECG signals, providing a powerful tool for the diagnosis of cardiovascular diseases.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153296-153307"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146785","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027936","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 Comprehensive Review of NLP Techniques for Military Terminologies and Information Operations on Social Media","authors":"Tamara Zhukabayeva;Zulfiqar Ahmad;Aigerim Yerimbetova;Madina Sambetbayeva;Duman Telman;Abdygalym Bayangali;Elmira Daiyrbayeva","doi":"10.1109/ACCESS.2025.3605354","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605354","url":null,"abstract":"This paper presents a comprehensive study aimed at systematically analyzing and evaluating natural language processing (NLP) techniques for military information operations, with a special focus on social media intelligence. Among an ever-growing complicated information environment, NLP methods like sentiment analysis, named entity recognition, and topic modeling have been essential in tracking online propaganda efforts, discovering emerging issues and threats globally with dialogues on military operations. These techniques make an impact on available decision making via situational awareness and getting the added extraction from volumes of unstructured data outputs thus increasing the overall strategic benefits to military organizations. There are technical and operational challenges concerning the use of NLP in a military context such as requirements for real-time data processing; language diversity; and maintaining data privacy while preserving ethical standards. To address these challenges, the study conducts an exhaustive survey of NLP methods, reviewing their range of applications, and highlights the relevance of several approaches for military information operations, with special emphasis on social media intelligence. The work further provides discussion on the comprehensive adoption of artificial intelligence (AI), edge computing, and multilingual NLP models for enhancing adaptability, efficiency, and transparency of the systems. It also extols the need for explainable AI (XAI) to improve accountability and trust by making term or even whole early warning systems derived from NLP analyses, transparent and interpretable for these military research applications with significant financial consequences. The paper also emphasizes the strategic importance of multilingual and multimodal analysis and the integration of specialized military lexicons to improve the contextual understanding of military discourse in social media environments. We also elucidate the important capabilities of NLP in enabling military operations to be responsive, rapid and data-driven while also adapting to the evolving nature of warfare. Key conclusions suggest that applying advanced NLP tools enhances situational awareness, enables timely threat detection, and supports more agile, data-informed decision-making within modern military operations. The paper shows a perspective to optimize NLP and AI technologies, leveraging various perspectives to benefit the operational needs of military and defense sectors in more data-rich environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154930-154947"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146650","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021165","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":"GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding","authors":"Minseong Kim;Jinyeong Park;Sungho Park;Jibum Kim","doi":"10.1109/ACCESS.2025.3604810","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3604810","url":null,"abstract":"Multi-modal approaches used for 3D CAD generation require substantial computational resources, necessitating efficient training. To address this, we propose GuideCAD, which leverages semantically rich visual-textual representations having only a small number of trainable parameters to generate 3D CAD models. Specifically, GuideCAD uses a mapping network that converts image embeddings into prefix embeddings, enabling a pretrained large language model to integrate visual and textual information. As a result, a transformer-based decoder predicts the construction sequence using the visual-textual embeddings in order to generate the 3D CAD model. For experimental evaluation, we construct a new dataset, referred to as GuideCAD, which consists of text-image pairs. Each pair includes a text prompt that represents a 3D CAD construction sequence and its corresponding 3D CAD image. Our experimental results show that GuideCAD generates comparably high-quality 3D CAD models while using approximately four times fewer parameters and achieving twice the training efficiency compared to fine-tuning approaches. We have released the source code and dataset for our method at: <uri>https://github.com/mskimS2/GuideCAD</uri>","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153406-153419"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146789","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027920","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 Two-Switch Step-Up Topology With Coupled Inductor for High Voltage Conversion","authors":"Kim-Anh Nguyen;Thai Anh Au Tran;Xuan Khanh Ho;Duong Thach Pham","doi":"10.1109/ACCESS.2025.3605292","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605292","url":null,"abstract":"This paper introduces a new non–isolated boost–type dc–dc converter that is applicable to PV/fuel cell sources and other low–voltage dc systems requiring high voltage gain and a compact structure. The proposed architecture incorporates two synchronized switches, a coupled magnetic element, a passive energy recovery unit, and a multi–stage voltage elevating network to achieve a very high output voltage while minimizing component stress and maintaining a simple structure. A smooth input current profile with minimal ripple is ensured by the input inductor, and conduction losses are lowered through current distribution across the switching devices. The passive clamp design enables the recovery of leakage energy and limits overvoltage across power devices, permitting the employment of low–voltage–rated MOSFETs to enhance the overall efficiency. A staged voltage boosting technique further increases the output without significantly increasing circuit complexity. Compared to existing topologies, the proposed converter demonstrates advantages in voltage boosting capability, stress reduction on switches, and reduction in the overall part count. Theoretical analysis, design procedures, and performance comparisons are thoroughly discussed to validate the proposed design. A 200 W prototype operating from a 24 V input to a 400 V output was simulated and built. Simulation and test results match theoretical predictions, with peak efficiencies of 95.2% and 94.1% at full load, confirming the converter’s suitability for compact, high–efficiency power systems including PV microinverters, battery storage, EV auxiliary modules, marine power, medical devices, and high–voltage loads such as plasma generators and AMOLED displays.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154326-154340"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146741","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021254","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":"Fault Protection Method for Low-Current Grounding Systems in Active Distribution Networks Based on an Improved Clustering Algorithm","authors":"Chen Xue;Jian Zhu;Shengmin Tan;Guojing Zhang;Chen Liu","doi":"10.1109/ACCESS.2025.3605355","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605355","url":null,"abstract":"With the increasing global focus on carbon neutrality and the development of renewable energy, a large number of distributed generation units have been integrated into the distribution network to enhance sustainability and reduce carbon emissions. As a result, fault signals often exhibit high-frequency, nonlinear, and weak characteristics, rendering traditional low-current grounding fault line selection methods ineffective. In this paper, by analyzing the differences between the transient zero-sequence currents of low-current grounding faults in active distribution networks, a fault protection method for low-current grounding systems based on an improved clustering algorithm with optimized initial cluster center selection is proposed. The proposed method involves filtering the transient zero-sequence currents, characterizing their phase differences using the cosine distance between each pair of zero-sequence currents, and performing clustering analysis with an improved k-means algorithm. By defining a range for the number of clusters k and determining the optimal value based on the within-cluster sum of squares (WCSS), the fault line can be accurately identified. Simulation results demonstrate that the method is applicable to both conventional low-current systems and low-current systems in active distribution networks, offering good practicality and anti-interference performance.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154545-154555"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146715","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021320","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":"CHULA: Custom Heuristic Uncertainty-Guided Loss for Accurate Land Title Deed Segmentation","authors":"Teerapong Panboonyuen;Chaiyut Charoenphon;Chalermchon Satirapod","doi":"10.1109/ACCESS.2025.3605218","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605218","url":null,"abstract":"Accurately segmenting land boundaries from Thai land title deeds is crucial for reliable land management and legal processes, but remains challenging due to low-quality scans, diverse layouts, and complex overlapping elements in documents. Existing methods often struggle with these difficulties, resulting in imprecise delineations that can cause disputes or inefficiencies. To address these issues, we propose CHULA, a novel Custom Heuristic Uncertainty-guided Loss tailored specifically for robust land title deed segmentation. CHULA uniquely combines domain-specific heuristic priors with uncertainty modeling in a unified loss function that effectively guides the model to focus on clearer regions while refining boundaries and suppressing noisy areas. Evaluated on a carefully curated Thai Land Title Deed Dataset, CHULA achieves an impressive 92.4% accuracy, significantly surpassing standard segmentation baselines. Our results highlight the promise of integrating uncertainty and heuristic knowledge to enhance segmentation accuracy in complex, real-world documents. The code is publicly available at <uri>https://github.com/kaopanboonyuen/CHULA</uri>","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"155047-155063"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146788","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021164","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":"Entropy-Based Data Selection for Language Models","authors":"Hongming Li;Yang Liu;Chao Huang","doi":"10.1109/ACCESS.2025.3605290","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605290","url":null,"abstract":"Modern language models (LMs) increasingly require two critical resources: computational resources and data resources. Data selection techniques can effectively reduce the amount of training data required for fine-tuning LMs. However, their effectiveness is closely related to computational resources, which always require a high compute budget. Owing to the resource limitations in practical fine-tuning scenario, we systematically reveal the relationship between data selection and uncertainty estimation of selected data. Although large language models (LLMs) exhibit exceptional capabilities in language understanding and generation, which provide new ways to alleviate data scarcity, evaluating data usability remains a challenging task. This makes efficient data selection indispensable. To mitigate these issues, we propose Entropy-Based Unsupervised Data Selection (EUDS) framework. Empirical experiments on sentiment analysis (SA), topic classification (Topic-CLS), and question answering (Q&A) tasks validate its effectiveness. EUDS establishes a computationally efficient data-filtering mechanism. Theoretical analysis and experimental results confirm the effectiveness of our approach. EUDS significantly reduces computational costs and improves training time efficiency with less data requirement. This provides an innovative solution for the efficient fine-tuning of LMs in the compute-constrained scenarios.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153713-153727"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146774","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027990","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":"Data-Driven Learning of Two-Stage Beamformers in Passive IRS-Assisted Systems With Inexact Oracles","authors":"Spyridon Pougkakiotis;Hassaan Hashmi;Dionysis Kalogerias","doi":"10.1109/ACCESS.2025.3605249","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605249","url":null,"abstract":"The purpose of this work is the development of an efficient data-driven and model-free unsupervised learning framework for achieving fully passive intelligent reflective surface (IRS)-assisted optimal joint short/long-term beamforming in wireless communication networks. Under this challenging setting, our contribution amounts to the design of novel IRS training schemes —termed iZoSGA herein— relying on a zeroth-order stochastic gradient ascent methodology, suitable for tackling nonconvex two-stage stochastic optimization problems with continuous uncertainty and unknown (or “black-box”) terms present in the corresponding objective function, via utilization of inexact short-term evaluation oracles. Our findings are as follows: We showcase that iZoSGA can operate under realistic and general assumptions, and establish its (non-asymptotic) convergence rate close to some stationary point of the associated two-stage (i.e., short/long-term) problem, particularly in cases where the second-stage (i.e., short-term) beamforming problem (e.g., transmit precoding) is solved inexactly using an arbitrary (inexact) algorithm. iZoSGA is applicable on a wide variety of IRS-assisted optimal beamforming settings, while also being able to operate without (cascaded) channel model assumptions or knowledge of channel statistics, and over arbitrary IRS physical configurations; thus, no active sensing capability at the IRS(s) is needed. Additionally, our approach bypasses the need of imposing challenging nonconvex unit-modulus constraints, typically associated with IRS parameter optimization. Several algorithmic variants of iZoSGA are numerically demonstrated to be particularly effective in a range of experiments pertaining to a well-studied MISO downlink model, including scenarios demanding physical IRS tuning (e.g., directly through varactor capacitances), even in large-scale regimes. Overall we demonstrate that, by leveraging the developed theory and its insights on the propagation of oracle errors, we can create highly efficient and scalable algorithms for the solution of general (possibly large-scale) IRS-assisted optimal beamforming problems, under realistic assumptions.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154984-155002"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146777","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021244","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}