IEEE Access最新文献

{"title":"Balancing Privacy and Utility in Split Learning: An Adversarial Channel Pruning-Based Approach","authors":"Afnan Alhindi;Saad Al-Ahmadi;Mohamed Maher Ben Ismail","doi":"10.1109/ACCESS.2025.3528575","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528575","url":null,"abstract":"Machine Learning (ML) has been exploited across diverse fields with significant success. However, the deployment of ML models on resource-constrained devices, such as edge devices, has remained challenging due to the limited computing resources. Moreover, training such models using private data is prone to serious privacy risks resulting from inadvertent disclosure of sensitive information. Split Learning (SL) has emerged as a promising technique to mitigate these risks through partitioning neural networks into the client and the server subnets. One should note that although only the extracted features are transmitted to the server, sensitive information can still be unwittingly revealed. Existing approaches addressing this privacy concern in SL struggle to maintain a balance of privacy and utility. This research introduces a novel privacy-preserving split learning approach that integrates: 1) Adversarial learning and 2) Network channel pruning. Specifically, adversarial learning aims to minimize the risk of sensitive data leakage while maximizing the performance of the target prediction task. Furthermore, the channel pruning performed jointly with the adversarial training allows the model to dynamically adjust and reactivate the pruned channels. The association of these two techniques makes the intermediate representations (features) exchanged between the client and the server models less informative and more robust against data reconstruction attacks. Accordingly, the proposed approach enhances data privacy without ceding the model’s performance in achieving the intended utility task. The contributions of this research were validated and assessed using benchmark datasets. The experiments demonstrated the superior defense ability, against data reconstruction attacks, of the proposed approach in comparison with relevant state-of-the-art approaches. In particular, the SSIM between the original data and the data reconstructed by the attacker, achieved by our approach, decreased significantly by 57%. In summary, the obtained quantitative and qualitative results proved the efficiency of the proposed approach in balancing privacy and utility for typical split learning frameworks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10094-10110"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838505","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993856","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":"Quantile Regression for Probabilistic Electricity Price Forecasting in the U.K. Electricity Market","authors":"Yuki Osone;Daisuke Kodaira","doi":"10.1109/ACCESS.2025.3528450","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528450","url":null,"abstract":"The volatility and uncertainty of electricity prices due to renewable energy sources create challenges for electricity trading, necessitating reliable probabilistic electricity-price forecasting (EPF) methods. This study introduces an EPF approach using quantile regression (QR) with general predictors, focusing on the UK market. Unlike market-specific models, this method ensures adaptability and reduces complexity. Using 1,132 days of training data, including electricity prices, demand forecasts, and generation forecasts obtained from UK electricity companies, results show that the proposed model achieved a mean absolute error of 18.27 [(£/MWh] for predicting volatile short-term spot market prices. The QR model achieved high predictive accuracy and stability, with only a 4–25% average pinball loss increases when the previous day’s prices (<inline-formula> <tex-math>$P_{t-1}$ </tex-math></inline-formula>) were excluded due to bidding deadlines. These findings demonstrate the model’s robustness and its potential to enhance market efficiency by providing reliable and simplified probabilistic forecasts, aiding stakeholders in mitigating risks and optimizing strategies.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10083-10093"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838567","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993495","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":"Predefined-Time H ∞ Cooperative Control for Multi-Robot Systems Based on Adjustable Prescribed Performance Control and Adaptive Command Filter","authors":"Haitao Liu;Weichen Li;Xin Huang;Xuehong Tian;Qingqun Mai","doi":"10.1109/ACCESS.2025.3529130","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3529130","url":null,"abstract":"A predefined-time <inline-formula> <tex-math>$H_{infty } $ </tex-math></inline-formula> coordinated formation controller with an adjustable prescribed performance function (PPF) and an adaptive command filter is proposed for multi-robot systems in this work. First, an adjustable prescribed performance function is developed to limit the angular error and adaptively adjust the state convergence performance subject to actuator saturation, which effectively avoids the singularity problem. Second, the “explosion of complexity” issue is solved by proposing a predefined-time adaptive command filter and accelerate the convergence time and improve filter precision. Third, the predefined-time <inline-formula> <tex-math>$H_{infty } $ </tex-math></inline-formula> control theory is developed to guarantee that the nonlinear system has global predefined-time stabilization and that the <inline-formula> <tex-math>$L_{2}$ </tex-math></inline-formula> gain is less than <inline-formula> <tex-math>$gamma $ </tex-math></inline-formula>. Fourth, the predefined-time <inline-formula> <tex-math>$H_{infty } $ </tex-math></inline-formula> coordinated formation controller for multi-robot systems (MRSs) is designed to achieve strong robustness to various disturbances. Finally, all the signals in the control system are bounded and converge within the predefined time, and the results of the virtual simulation experiments verify the validity and performance of the MRSs.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"12055-12067"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839388","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993011","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":"Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model","authors":"Mo Shen;Rongrong Sun;Wen Ye","doi":"10.1109/ACCESS.2025.3528882","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528882","url":null,"abstract":"In clinical environments, the quality of low-dose computerized tomography (LDCT) images is inevitably degraded by artifacts and noise. Accurate and clinically relevant image quality assessment (IQA) for LDCT images is crucial to provide appropriate medical care. However, due to the absence of reference images and inadequate understanding of the human visual system (HVS), there is currently a lack of effective IQA methods. To address this problem, this paper proposes a no-reference IQA method that emulates the perceptual characteristics of the HVS. The method is based on the use of sparse representation in conjunction with a just noticeable distortion (JND) model. Specifically, for each tested image, a patch-level JND map is first calculated to indicate the noticeable level of distortion in different regions. Subsequently, noticeable patches of the image are encoded via sparse representation, followed by max pooling to obtain sparse features. Finally, these sparse features, along with the sorted JND values, are combined as overall features into a regression model to predict an objective quality score. By combining two types of features, our method can measure the quality from the perspectives of both local spatial structures and visual distortion sensitivity. Our method is evaluated on the LDCTIQAC2023 database, and the experimental results demonstrate the effectiveness of our method, which correlates reasonably well with the radiologists’ subjective scores.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10422-10431"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838566","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993853","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":"IRSnet: An Implicit Residual Solver and Its Unfolding Neural Network With 0.003M Parameters for Total Variation Models","authors":"Yuanhao Gong","doi":"10.1109/ACCESS.2025.3528637","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528637","url":null,"abstract":"Solving total variation problems is fundamentally important for many computer vision tasks, such as image smoothing, optical flow estimation and 3D surface reconstruction. However, the traditional iterative solvers require a large number of iterations to converge, while deep learning solvers have a huge number of parameters, hampering their practical deployment. To address these issues, this paper first introduces a novel iterative algorithm that is 6 ~ 75 times faster than previous iterative methods. The proposed iterative method converges and converges to the optimal solution. These two facts are theoretically guaranteed and numerically confirmed, respectively. Then, we generalize this algorithm to a compact implicit neural network that has only 0.003M parameters. The network is shown to be more effective and efficient. Thanks to the small number of parameters, the proposed network can be applied in a wide range of applications where total variation is imposed. The source code for the iterative solver and the neural network is publicly available at <uri>https://github.com/gyh8/IRS</uri>.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10289-10298"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838572","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993431","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":"IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition","authors":"George Karantaidis;Athanasios Pantsios;Ioannis Kompatsiaris;Symeon Papadopoulos","doi":"10.1109/ACCESS.2025.3528633","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528633","url":null,"abstract":"Deep learning techniques have achieved significant success in Synthetic Aperture Radar (SAR) target recognition using predefined datasets in static scenarios. However, real-world applications demand that models incrementally learn new information without forgetting previously acquired knowledge. The challenge of catastrophic forgetting, where models lose past knowledge when adapting to new tasks, remains a critical issue. In this paper, we introduce IncSAR, an incremental learning framework designed to tackle catastrophic forgetting in SAR target recognition. IncSAR combines the power of a Vision Transformer (ViT) and a custom-designed Convolutional Neural Network (CNN) in a dual-branch architecture, integrated via a late-fusion strategy. Additionally, we explore the use of TinyViT to reduce computational complexity and propose an attention mechanism to dynamically enhance feature representation. To mitigate the speckle noise inherent in SAR images, we employ a denoising module based on a neural network approximation of Robust Principal Component Analysis (RPCA), leveraging a simple neural network for efficient noise reduction in SAR imagery. Moreover, a random projection layer improves the linear separability of features, and a variant of Linear Discriminant Analysis (LDA) decorrelates extracted class prototypes for better generalization. Extensive experiments on the MSTAR, SAR-AIRcraft-1.0, and OpenSARShip benchmark datasets demonstrate that IncSAR significantly outperforms state-of-the-art approaches, achieving a 99.63% average accuracy and a 0.33% performance drop, representing an 89% improvement in retention compared to existing techniques. The source code is available at <uri>https://github.com/geokarant/IncSAR</uri>.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"12358-12372"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838563","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993496","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":"Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models","authors":"Stella Pantopoulou;Matthew Weathered;Darius Lisowski;Lefteri H. Tsoukalas;Alexander Heifetz","doi":"10.1109/ACCESS.2025.3526438","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3526438","url":null,"abstract":"We benchmark performance of long-short term memory (LSTM) network machine learning model and autoregressive integrated moving average (ARIMA) statistical model in temporal forecasting of distributed temperature sensing (DTS). Data in this study consists of fluid temperature transient measured with two co-located Rayleigh scattering fiber optic sensors (FOS) in a forced convection mixing zone of a thermal tee. We treat each gauge of a FOS as an independent temperature sensor. We first study prediction of DTS time series using Vanilla LSTM and ARIMA models trained on prior history of the same FOS that is used for testing. The results yield maximum absolute percentage error (MaxAPE) and root mean squared percentage error (RMSPE) of 1.58% and 0.06% for ARIMA, and 3.14% and 0.44% for LSTM, respectively. Next, we investigate zero-shot forecasting (ZSF) with LSTM and ARIMA trained on history of the co-located FOS only, which is advantageous when limited training data is available. The ZSF MaxAPE and RMSPE values for ARIMA are comparable to those of the Vanilla use case, while the error values for LSTM increase. We show that in ZSF, performance of LSTM network can be improved by training on most correlated gauges between the two FOS, which are identified by calculating the Pearson correlation coefficient. The improved ZSF MaxAPE and RMSPE for LSTM are 4.4% and 0.33%, respectively. Performance of ZSF LSTM can be further enhanced through transfer learning (TL), where LSTM is re-trained on a subset of the FOS that is the target of forecasting. We show that LSTM pre-trained on correlated dataset and re-trained on 30% of testing target dataset achieves MaxAPE and RMSPE values of 2.32% and 0.28%, respectively.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10252-10264"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838524","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993846","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":"Oculomotor Plant Mathematical Model in Kalman Filter Form With Peak Velocity-Based Neural Pulse for Continuous Gaze Prediction","authors":"Dmytro Katrychuk;Dillon J. Lohr;Oleg V. Komogortsev","doi":"10.1109/ACCESS.2025.3528104","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528104","url":null,"abstract":"An oculomotor plant mathematical model (OPMM) employs physical and neurological characteristics of human visual system to define its dynamics. One of its most prominent applications in modern eye-tracking pipelines was hypothesized to be latency reduction via the means of eye movement prediction. However, this use case was only explored with OPMMs originally designed for saccade simulation. Such models typically relied on the neural pulse control being estimated from intended saccade amplitude - a property that becomes fully observed only after a saccade already ended, which greatly limits the model’s prediction capabilities. We present the first OPMM designed with the prediction task in mind. We draw our inspiration from a “peak velocity - amplitude” main sequence relationship and propose to use saccade’s peak velocity for neural pulse estimation. We additionally extend the prior work by evaluating the proposed model on the largest to date pool of 322 subjects against the naive zero displacement baseline and a long short-term memory (LSTM) neural network.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"11544-11559"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839497","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993865","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":"Arranging a Pool of Functional Test Sequences for Variable In-Field Test Periods","authors":"Irith Pomeranz","doi":"10.1109/ACCESS.2025.3528741","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528741","url":null,"abstract":"High workloads applied to a system cause chips to be more susceptible to aging effects that may eventually result in hardware defects. The detection of the defects requires tests for delay faults to be applied in-field. Both scan-based tests and functional test sequences are important to apply. In-field test periods vary in length. Therefore, test sets of both types should be arranged such that every test period would be utilized for targeting the most likely to occur faults. This is preferred over the alternative where each test period is used for achieving the highest possible fault coverage since the highest possible fault coverage may be achieved without detecting the most likely to occur faults. This article considers the problem of arranging a pool of functional test sequences to match different in-field test periods when the goal is to ensure that the most likely to occur faults are detected in every test period. The procedure described in this article produces a series of solutions with subsets of increasing lengths of the pool (subpools) to detect subsets of transition faults of increasing sizes. The increase in the length of every subpool in the series is minimum or close-to-minimum relative to the length of the previous subpool. The procedure is implemented in an academic simulation environment and applied to benchmark circuits to demonstrate its effectiveness.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10009-10021"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838502","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993107","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":"Diagnosis of Coronary Heart Disease Through Deep Learning-Based Segmentation and Localization in Computed Tomography Angiography","authors":"Bo Zhao;Jianjun Peng;Ce Chen;Yongyan Fan;Kai Zhang;Yang Zhang","doi":"10.1109/ACCESS.2025.3528638","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528638","url":null,"abstract":"Coronary heart disease (CHD), a leading cause of global mortality, requires precise and early diagnosis for effective intervention. Coronary computed tomography angiography (CCTA) has emerged as a non-invasive modality for detailed coronary artery visualization; however, automatic and accurate segmentation of coronary structures from CCTA images remains challenging. Conventional convolutional neural networks (CNNs), despite their success in medical imaging, face limitations in capturing the complex, long-range dependencies in coronary artery images due to their localized receptive fields. Vision transformers, with their self-attention mechanisms, offer a global perspective, yet demand extensive data and computational resources, making them less adaptable for the often limited medical imaging datasets. This research addresses these challenges by proposing TransCHD, a hybrid CNN-Transformer architecture developed for coronary artery segmentation in CCTA. TransCHD incorporates a Contextual Representation Learning (CRL) module and a Spatially-Aware Feature (SAF) module, enabling both local feature extraction and global contextual awareness within a unified architecture. The CRL module mitigates spatial continuity disruptions caused by standard patch-based transformers, while the SAF module enhances spatial locality and preserves fine-grained anatomical details essential for accurate segmentation. The segmentation outcomes are clinically significant as they provide quantitative assessments of arterial stenosis, plaque characterization, and ischemia-prone regions, supporting risk assessment and treatment planning. Trained and evaluated on the CorArtTS2020 dataset, TransCHD achieved superior performance compared to state-of-the-art CNN- and transformer-based models, with a Dice score of 0.81 and an Intersection over Union (IoU) of 0.65. Results show that our proposed TransCHD is effective in CCTA segmentation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10177-10193"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838557","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993169","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}