IEEE Access最新文献

{"title":"XRGuard: A Model-Agnostic Approach to Ransomware Detection Using Dynamic Analysis and Explainable AI","authors":"M. Adnan Alvi;Zunera Jalil","doi":"10.1109/ACCESS.2025.3553562","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553562","url":null,"abstract":"Ransomware remains a persistent and evolving cybersecurity threat, demanding advanced and adaptable detection strategies. Traditional methods often fall short as signature-based systems are easily circumvented by emerging ransomware variants, while techniques like obfuscation and polymorphism add complexity to the detection process. Although machine learning and deep learning techniques present viable solutions, the opacity of complex black-box models can hinder their application in critical security environments. This paper introduces XRGuard, a novel ransomware detection framework that utilizes machine learning techniques to analyze Event Tracing for Windows (ETW) logs, identifying critical file I/O patterns indicative of ransomware attacks. By incorporating XAI techniques such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), XRGuard bridges the trust gap associated with complex machine learning models by providing transparent and interpretable explanations for its decisions. Experimental results demonstrate that XRGuard achieves a 99.69% accuracy rate with an exceptionally low false positive rate of 0.5%. By enhancing detection accuracy and offering clear explanations of its operations, XRGuard not only improves security but also fosters trust and a deeper understanding of ransomware behaviors.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"53159-53170"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740405","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":"Understanding Flaky Tests Through Linguistic Diversity: A Cross-Language and Comparative Machine Learning Study","authors":"Azeem Ahmad;Xin Sun;Muhammad Rashid Naeem;Yasir Javed;Mohammad Akour;Kristian Sandahl","doi":"10.1109/ACCESS.2025.3553626","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553626","url":null,"abstract":"Software development is significantly impeded by flaky tests, which intermittently pass or fail without requiring code modifications, resulting in a decline in confidence in automated testing frameworks. Code smells (i.e., test case or production code) are the primary cause of test flakiness. In order to ascertain the prevalence of test smells, researchers and practitioners have examined numerous programming languages. However, one isolated experiment was conducted, which focused solely on one programming language. Across a variety of programming languages, such as Java, Python, C++, Go, and JavaScript, this study examines the predictive accuracy of a variety of machine learning classifiers in identifying flaky tests. We compare the performance of classifiers such as Random Forest, Decision Tree, Naive Bayes, Support Vector Machine, and Logistic Regression in both single-language and cross-language settings. In order to ascertain the impact of linguistic diversity on the flakiness of test cases, models were trained on a single language and subsequently tested on a variety of languages. The following key findings indicate that Random Forest and Logistic Regression consistently outperform other classifiers in terms of accuracy, adaptability, and generalizability, particularly in cross-language environments. Additionally, the investigation contrasts our findings with those of previous research, exhibiting enhanced precision and accuracy in the identification of flaky tests as a result of meticulous classifier selection. We conducted a thorough statistical analysis, which included t-tests, to assess the importance of classifier performance differences in terms of accuracy and F1-score across a variety of programming languages. This analysis emphasizes the substantial discrepancies between classifiers and their effectiveness in detecting flaky tests. The datasets and experiment code utilized in this study are accessible through an open source GitHub repository to facilitate reproducibility is available at: <uri>https://github.com/PELAB-LiU/FlakyCrossLanguage</uri>. Our results emphasize the effectiveness of probabilistic and ensemble classifiers in improving the reliability of automated testing, despite certain constraints, including the potential biases introduced by language-specific structures and dataset variability. This research provides developers and researchers with practical insights that can be applied to the mitigation of flaky tests in a variety of software environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"54561-54584"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937160","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748919","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":"Deep Classification of Algarrobo Trees in Seasonally Dry Forests of Peru Using Aerial Imagery","authors":"Wilson Castro;Himer Avila-George;William Nauray;Roenfi Guerra;Jorge Rodriguez;Jorge Castro;Miguel de-la-Torre","doi":"10.1109/ACCESS.2025.3553752","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553752","url":null,"abstract":"Seasonally dry forests require tailored strategies to address the challenges posed by deforestation and desertification, particularly for the conservation of protected tree species. Efforts to defend protected flora involve maintaining accurate records of superior specimens of seed-producer trees (plus trees), to support informed management decisions in designated areas. In this paper, a methodology is proposed for the automated classification of plus algarrobo trees (Neltuma pallida), based on RGB aerial imagery and deep learning classifiers. As a proof of concept, three state-of-the-art approaches were evaluated in selected zones of interest, and a new application-specific architecture called AlgarroboNet was proposed for efficient classification of plus algarrobo trees. Initially, a dataset containing the geographic and phenological characteristics of algarrobo trees was provided by the Peru National Forest Service. Subsequent in-situ evaluations retrieved detailed morphometric measurements of plus trees, along with aerial imagery for both plus and non-plus specimens. After correction and segmentation, a balanced database was prepared to evaluate the four deep classifiers. The performance of each approach was summarized using both accuracy and <inline-formula> <tex-math>$F_{1}$ </tex-math></inline-formula>-measure, following a hold-out validation strategy with 30 trials. The results reveal that state-of-the-art approaches show a <inline-formula> <tex-math>$F_{1}$ </tex-math></inline-formula>-measure that ranges between 0.92 and 0.99 among the models, presenting a trade-off between computational resources and accuracy. Through a detailed analysis, the proposed methodology shows potential for large-scale monitoring and characterization of plus algarrobo trees, and suggest being suitable for implementation, aiming to maintain an up-to-date inventory and enforce reforestation programs.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"54960-54975"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937278","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761595","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":"Deep Learning-Based MRI Brain Tumor Segmentation With EfficientNet-Enhanced UNet","authors":"Pradeep Kumar Tiwary;Prashant Johri;Alok Katiyar;Mayur Kumar Chhipa","doi":"10.1109/ACCESS.2025.3554405","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3554405","url":null,"abstract":"Medical image segmentation plays a critical role in the field of medical image processing. Precisely delineating brain tumor areas from multimodal MRI scans is crucial for clinical diagnosis and predicting patient outcomes. However, challenges arise from similar intensity patterns, varying tumor shapes, and indistinct boundaries, which complicate brain tumor segmentation. Traditional segmentation networks like UNet face difficulties in capturing comprehensive long-range dependencies within the feature space due to the limitations of CNN receptive fields. This limitation is particularly significant in tasks requiring detailed predictions such as brain tumor segmentation. Inspired by these constraints, this study suggests incorporating EfficientNet as an encoder within UNet, with a thorough reassessment of its fundamental components: the encoder, bottleneck, and skip connections. EfficientNet replaces UNet’s encoder, initially frozen to retain learned features from pre-trained weights, adept at extracting detailed features crucial for precise segmentation like brain tumors from MRI scans. Preserving UNet’s bottleneck compresses EfficientNet’s outputs, while skip connections maintain spatial integrity during decoder upsampling. The decoder reconstructs the original image size by merging encoder-decoder features, refining boundaries with convolutional layers for accurate clinical insights. The study conducted multiclass operations on the Brain-Tumor.npy dataset from Kaggle, consisting of 3064 T1-weighted contrast-enhanced images from 233 patients with meningioma (708 slices), glioma (1426 slices), and pituitary tumor (930 slices). Experimental findings in brain tumor segmentation tasks show that the proposed model achieves performance on par with or better than recent CNN or Transformer models. Specifically, the model achieves an accuracy of 0.9925 and a loss of 0.2991 on the dataset.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"54920-54937"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10938151","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761296","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":"Operational and Planning Perspectives on Battery Swapping and Wireless Charging Technologies: A Multidisciplinary Review","authors":"Sarah M. Kandil;Akmal Abdelfatah;Maher A. Azzouz","doi":"10.1109/ACCESS.2025.3554336","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3554336","url":null,"abstract":"The electrification of the transportation system is considered one of the most viable solutions to address the pressing need to shift towards sustainable development. However, one of the major challenges to the rapid adoption of Electric Vehicles (EVs) is the lack of the right charging infrastructure where and when it is needed. Motivated by the necessity for a multidisciplinary approach, this study addresses the complex operational and planning challenges involved in integrating transportation and electrical networks for effective EV charging. Thus, this research aims to survey the literature to identify the adopted technologies, and the application and allocation of the right mix of the technologies to better serve the seamless adoption of EVs. That problem is multifaced where transportation network requirements and the electrical grid are important to support the charging loads at the needed time. The literature survey adopts the PRISMA methodology, contributing to the existing literature by highlighting the following shortcomings: 1) the problem of allocating the charging technology is either purely viewed from a transportation or an electrical perspective, 2) there is a gap in adopting both networks’ requirements comprehensively, 3) the literature predominately focuses on a single technology either battery swapping or wireless charging, 4) introducing new technologies highlights the impact of each on both networks in terms of return of investment, traffic flows, and power grids operational conditions, 5) research direction is focused more towards operation and routing while service allocation is relatively new and has not yet been extensively explored, and 6) transportation network research focuses on a static representation of the transportation network and EV demand. This study’s main contribution, besides identifying critical gaps in the existing literature and possible future research directions, is the proposal of a novel framework that integrates multiple charging technologies. This framework is designed to optimize infrastructure deployment, enhancing the efficiency and economic viability of EV charging systems across both transportation and electrical networks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52775-52806"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10938089","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726261","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":"Dual-Channel Dynamic Gated Spatio-Temporal Graph for Traffic Flow Forecasting","authors":"Chao Wang;Jun-Feng Hao;He Huang;Wang Zou;Xia Sun;Ting Peng","doi":"10.1109/ACCESS.2025.3553535","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553535","url":null,"abstract":"Traffic flow forecasting is a critical and essential technology in the field of Intelligent Transportation Systems (ITS), as it plays a pivotal role in optimizing traffic management, improving road safety, and enhancing the overall efficiency of transportation networks. However, current research neglects the relationships between the local and global traffic flow data. Additionally, the predefined static graph structure fails to adequately capture the dynamic spatial features of traffic flow. To address the these challenges, this paper proposes a Dual-Channel Dynamic Gated Spatio-Temporal graph network (DC-DGST) for traffic flow prediction. We consider hourly slices as the local feature and daily slices to be the global feature of traffic flow. The DC-DGST framework employs a dual-channel structure to capture spatiotemporal dependencies between global and local features. It transforms the predefined static graph into a dynamic graph, enabling the establishment of connections between input data and historical information. Furthermore, we design gated spatio-temporal blocks based on residual structures within the spatio-temporal module. Specifically, we utilize Graph Gated Neural Networks (GGNNs) to learn and integrate both static and dynamic graphs, while Transformer encoders are used to capture long-range dependencies in the temporal sequence. We conducted a series of experiments on four publicly available benchmark datasets: PEMS03, PEMS04, PEMS07, and PEMS08. The results demonstrate that our model significantly outperforms baseline models. Moreover, the dual-channel structure effectively captures the correlation between local and global traffic flow features, while the dynamic graph enhances the model’s overall performance.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52995-53006"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937097","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726263","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":"FetalMovNet: A Novel Deep Learning Model Based on Attention Mechanism for Fetal Movement Classification in US","authors":"Musa Turkan;Emre Dandil;Furkan Erturk Urfali;Mehmet Korkmaz","doi":"10.1109/ACCESS.2025.3553548","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553548","url":null,"abstract":"Automated classification of fetal movements in ultrasound (US) videos is critical for assessing fetal well-being and detecting potential complications during pregnancy. This study introduces FetalMovNet, a novel deep learning model that incorporates an attention mechanism to improve the classification of fetal movement in US video sequences. The model integrates convolutional neural networks (CNN) for feature extraction and an attention mechanism to capture spatio-temporal patterns, significantly improving classification performance of fetal movements. To evaluate FetalMovNet, we construct a new dataset containing fetal movements in US across seven different anatomical structures-head, body, arm, hand, heart, leg, and foot. Experimental results show that FetalMovNet achieves an accuracy of 0.9887, precision of 0.9871, recall of 0.9910, and an F1-score of 0.9891, outperforming state-of-the-art CNN and CNN-LSTM architectures. Ablation studies confirm the effectiveness of the attention mechanism, with FetalMovNet achieving an area under curve (AUC) score of 0.9957, compared to 0.9471 for CNN and 0.9543 for CNN-LSTM. The proposed FetalMovNet model provides a robust and clinically applicable tool for real-time fetal movement monitoring, reducing the need for manual assessment and improving prenatal care.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52508-52527"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726422","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":"Techno-Economic and Environmental Analysis of Solar PV System at Sher-e-Bangla National Cricket Stadium: A Comprehensive Case Study","authors":"Mohammad Ariful Islam Rafi;Md Sajid Hasan;Imam-Ur-Rashid;Md Manzurul Hasan;Jawadul Alam Chowdhury;Moshiur Rahman Sohan;Nahid A. Jahan;M. Mofazzal Hossain","doi":"10.1109/ACCESS.2025.3553636","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3553636","url":null,"abstract":"The proposed rooftop solar photovoltaic (PV) system at the Sher-e-Bangla National Cricket Stadium (SBNCS) demonstrates a sustainable energy solution addressing Bangladesh’s energy challenges. The system has a capacity of 83.2 kWp and is estimated to generate 129.5 MWh of energy annually. This deployment reduces reliance on fossil fuels and contributes to global Sustainable Development Goal 7 (SDG7). The performance evaluation reveals a Performance Ratio (PR) of 79.4%, ensuring efficient solar resource utilization. Economically, the project involves a total investment of <inline-formula> <tex-math>${$}$ </tex-math></inline-formula>101,031, achieving annual energy cost savings of <inline-formula> <tex-math>${$}$ </tex-math></inline-formula>5,370. Financial feasibility metrics include a Net Present Value (NPV) of <inline-formula> <tex-math>${$}$ </tex-math></inline-formula>99,131.5, an Internal Rate of Return (IRR) of 6%, and a Payback Period (PBP) of 13 years. Furthermore, the system reduces 50 tons of CO2 emissions annually, resulting in a Social Cost of Carbon (SCC) savings of <inline-formula> <tex-math>${$}$ </tex-math></inline-formula>77,064 over its 25-year lifespan. The project’s Levelized Cost of Energy (LCOE) is calculated as <inline-formula> <tex-math>${$}$ </tex-math></inline-formula>0.03/kWh, reflecting its long-term cost-effectiveness. This analysis highlights the economic, environmental, and performance benefits of implementing a rooftop solar PV system at SBNCS, offering a scalable model for integrating renewable energy into and other stadiums and large infrastructure. This study can aid in the integration of renewable energy into the grid and assist policymakers in facilitating the future energy storage systems and expanding grid-tied operations for enhanced sustainability.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52658-52682"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937237","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726376","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":"QRS-Trs: Style Transfer-Based Image-to-Image Translation for Carbon Stock Estimation in Quantitative Remote Sensing","authors":"Zhenyu Yu;Jinnian Wang;Hanqing Chen;Mohd Yamani Idna Idris","doi":"10.1109/ACCESS.2025.3554045","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3554045","url":null,"abstract":"Forests serve as vital carbon reservoirs, reducing atmospheric CO2 and mitigating climate change. Monitoring carbon stocks typically combines ground-based data with satellite remote sensing, yet accuracy remains a challenge. This study analyzes Huize County, China, using GF-1 WFV and Landsat TM images and introduces the Quantitative Remote Sensing Transformer (QRS-Trs), which leverages style transfer and attention mechanisms to enhance carbon stock estimation as an image-to-image translation task. QRS-Trs demonstrates three advantages: 1) Swin-Pix2Pix effectively reduces inter-domain discrepancies caused by sensor and lighting variations while excelling in de-clouding, outperforming Pix2Pix. 2) It incorporates a median filter to eliminate anomalies and a mask module to exclude non-target areas, achieving MAE =16.29 Mg/ha, RMSE =29.38 Mg/ha, <inline-formula> <tex-math>$R^{2} =0.71$ </tex-math></inline-formula>, and SSIM =0.75. 3) Applied to multi-year data, from 2005 to 2020, 44.04% of the area showed increased carbon stock, 10.22% decreased, and 45.74% remained unchanged. While QRS-Trs performs well, its generalization to diverse ecological conditions depends on high-quality training data. Nevertheless, this study provides a robust approach for high-resolution carbon stock estimation, contributing to improved forest carbon sink management.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"52726-52737"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937715","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726510","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":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning With Adaptive Quantization and Differential Privacy","authors":"Emre Ardıç;Yakup Genç","doi":"10.1109/ACCESS.2025.3554138","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3554138","url":null,"abstract":"Federated learning (FL) is a distributed machine learning method where multiple devices collaboratively train a model under the management of a central server without sharing underlying data. One of the key challenges of FL is the communication bottleneck caused by variations in connection speed and bandwidth across devices. Therefore, it is essential to reduce the size of transmitted data during training. Additionally, there is a potential risk of exposing sensitive information through the model or gradient analysis during training. To address both privacy and communication efficiency, we combine differential privacy (DP) and adaptive quantization methods. We use Laplacian-based DP to preserve privacy, which is relatively underexplored in FL and offers tighter privacy guarantees than Gaussian-based DP. We propose a simple and efficient global bit-length scheduler using round-based cosine annealing, along with a client-based scheduler that dynamically adapts based on client contribution estimated through dataset entropy analysis. We evaluate our approach through extensive experiments on CIFAR10, MNIST, and medical imaging datasets, using non-IID data distributions across varying client counts, bit-length schedulers, and privacy budgets. The results show that our adaptive quantization methods reduce total communicated data by up to 52.64% for MNIST, 45.06% for CIFAR10, and 31% to 37% for medical imaging datasets compared to 32-bit float training while maintaining competitive model accuracy and ensuring robust privacy through DP.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"54322-54337"},"PeriodicalIF":3.4,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10937694","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748832","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}