IEEE Access最新文献_第10页

MixLVMM: A Mixture of Lightweight Vision Mamba Model for Enhancing Skin Lesion Segmentation Across High Tone Variability MixLVMM：混合轻量视觉曼巴模型增强皮肤病变分割跨高音调变异性

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-11 DOI: 10.1109/ACCESS.2025.3588476

Mohamed Lamine Allaoui;Mohand Saïd Allili

{"title":"MixLVMM: A Mixture of Lightweight Vision Mamba Model for Enhancing Skin Lesion Segmentation Across High Tone Variability","authors":"Mohamed Lamine Allaoui;Mohand Saïd Allili","doi":"10.1109/ACCESS.2025.3588476","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588476","url":null,"abstract":"Accurate skin lesion segmentation remains a critical challenge in automated dermatological diagnosis due to heterogeneous lesion presentations, ambiguous boundaries, imaging artifacts, and significant variability in skin and lesion tones across diverse populations. Current segmentation methods inadequately address these multifaceted complexities, particularly failing to handle extreme tone variations that can lead to diagnostic bias. To address these limitations, we present the Mixture of Lightweight Vision Mamba Model (MixLVMM), a novel expert-based framework that enhances segmentation performance across high tone variability through specialized processing. Our approach employs a Siamese network with triplet loss as a gate mechanism to categorize lesions based on tonal characteristics, routing each image to specialized Vision Mamba Model (VMM) experts optimized for specific lesion categories. Each expert utilizes a U-shaped architecture incorporating Focused Vision Mamba blocks and Adaptive Salient Region Attention modules to capture lesion-specific features while maintaining computational efficiency. Comprehensive evaluation on ISIC and PH2 datasets demonstrates that MixLVMM achieves superior segmentation performance with an average Dice coefficient of 93%, surpassing state-of-the-art methods while maintaining efficiency with only 2.5M parameters. These results establish MixLVMM as a robust solution for addressing tone-related segmentation challenges in clinical dermatology, offering both high accuracy and practical deployment feasibility for real-world applications. Additional materials and code will be available at <uri>https://github.com/MOHAMEDLamine77/MixLVMM</uri>","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"121234-121249"},"PeriodicalIF":3.4,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11078245","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646478","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}

引用次数: 0

Carbon Black-Coated Fabric Blend as Piezoresistive Flexible Pressure Sensor for Motion Monitoring Applications 用于运动监测应用的压阻式柔性压力传感器——炭黑涂层织物混纺

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-11 DOI: 10.1109/ACCESS.2025.3588328

R. Srinivasan;A. Ravi Sankar

{"title":"Carbon Black-Coated Fabric Blend as Piezoresistive Flexible Pressure Sensor for Motion Monitoring Applications","authors":"R. Srinivasan;A. Ravi Sankar","doi":"10.1109/ACCESS.2025.3588328","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588328","url":null,"abstract":"Flexible pressure sensors (FPSs) have garnered significant interest among researchers focusing on wearable electronics for motion recognition, health care, rehabilitation therapy, athletic performance monitoring, and more applications. Recently, fabrics known for their flexibility and comfort have become popular substrates for fabricating various flexible sensors. Of these flexible sensors, piezoresistive devices are favored for their simplicity and notable sensitivity to physical movements. This study presents a fabric composite created by coating a viscose staple fiber/linen blend with functionalized conductive carbon black (CB) using a simple drop-coating method and evaluates its pressure-sensing performance. The FPS with optimum CB content exhibited sensitivities of 41.1 kPa<inline-formula> <tex-math>${}^{mathbf {-1}}$ </tex-math></inline-formula> and 1.4 kPa<inline-formula> <tex-math>${}^{mathbf {-1}}$ </tex-math></inline-formula> in the pressure ranges of 0-1 kPa and 1-20 kPa, respectively. With a low detection limit of 10 Pa, a response time of 16 ms, a relaxation time of 63 ms, durability exceeding 5,400 cycles, and stable performance in various ambient conditions, the FPS has exhibited potential for applications in bending motion monitoring and information transmission.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124234-124249"},"PeriodicalIF":3.4,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11078241","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680831","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}

引用次数: 0

Rectified Tangent Activation (RTA): A Novel Activation Function for Enhanced Deep Learning Performance 修正正切激活（RTA）：一种增强深度学习性能的新型激活函数

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3587602

Gaurav Kumar Pandey;Sumit Srivastava

{"title":"Rectified Tangent Activation (RTA): A Novel Activation Function for Enhanced Deep Learning Performance","authors":"Gaurav Kumar Pandey;Sumit Srivastava","doi":"10.1109/ACCESS.2025.3587602","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3587602","url":null,"abstract":"In deep learning, activation functions (AFs) influence a model’s performance, convergence rate, and generalization capability. Conventional activation functions such as ReLU, Swish, ELU, and Tanh have been widely utilized, each offering distinct advantages but also exhibiting intrinsic drawbacks. ReLU is computationally efficient but susceptible to the “dying ReLU” phenomenon, whereas Tanh has saturation problems in both its positive and negative ranges. This study presents the Rectified Tangent Activation (RTA) function, an innovative activation function developed to overcome these restrictions by integrating advantageous features of ReLU, Swish, ELU, and Tanh. We assess the efficacy of RTA by a comparison study with five prevalent activation functions: ELU, ReLU, Swish, and Tanh, utilizing four distinct datasets—CIFAR-10, CIFAR-100, Fashion MNIST, and Chest X-ray. The findings demonstrate that RTA regularly attains superior performance, ranking first on the CIFAR-100, Fashion MNIST, and Chest X-ray datasets, while achieving a robust second place on CIFAR-10, trailing only ELU. The versatility of RTA across diverse data sets, such as image classification and medical imaging, underscores its potential as a versatile AF for numerous deep-learning applications. Our findings indicate that RTA can alleviate problems such as gradient saturation and convergence delay while improving overall accuracy. Considering these encouraging outcomes, RTA offers a persuasive alternative for deep learning practitioners aiming for strong model performance with reduced computing demands.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"120028-120039"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11075670","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641042","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}

引用次数: 0

MulMatch-CL: A Semi-Supervised Teacher-Student Framework for Robust Crop Segmentation in UAV Imagery MulMatch-CL：用于无人机图像鲁棒作物分割的半监督师生框架

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3586498

Xiaoyu Xu;Dafang Zou;Jinding Zou;Shouhui Xia;Weiguo Sheng

{"title":"MulMatch-CL: A Semi-Supervised Teacher-Student Framework for Robust Crop Segmentation in UAV Imagery","authors":"Xiaoyu Xu;Dafang Zou;Jinding Zou;Shouhui Xia;Weiguo Sheng","doi":"10.1109/ACCESS.2025.3586498","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3586498","url":null,"abstract":"Accurate crop segmentation using unmanned aerial vehicle (UAV) imagery is essential for efficient crop monitoring and management. While Transformer-based architectures have demonstrated exceptional performance in segmentation tasks, their application to UAV imagery remains challenging owing to limited labeled data and noisy annotations. To address these challenges, this study proposes MulMatch-CL, a novel teacher-student architecture that integrates the semi-supervised MulMatch framework with Confident Learning (CL). The proposed MulMatch component employs consistency regularization and multiple strong augmentation streams to effectively utilize unlabeled data and enhance model generalization. A teacher model is first trained on both labeled and unlabeled data to generate pixel-wise probability distributions. Confident Learning then identifies and filters noisy labels, refining the labeled dataset. The cleaned dataset, combined with the unlabeled data, is used to train a student model, resulting in a more robust segmentation performance. Experimental results on the Barley Remote Sensing Dataset show that MulMatch-CL achieves 78.42% mIoU, 89.10% pixel Acc, and 87.58% F1 score, outperforming supervised baselines, robust learning strategies, and semi-supervised methods. Ablation studies further confirm that both Confident Learning and MulMatch independently enhance performance, improving mIoU by 2.36% and 4.28% respectively, while their integration yields a 6.08% improvement over the baseline. These results demonstrate that MulMatch-CL provides a robust solution for applying Transformer models to UAV-based crop segmentation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"122914-122927"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11075738","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144666118","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}

引用次数: 0

MVTC-Sec: Lightweight Timestamp Correlation for Securing RPL Against DIO Replay Attacks MVTC-Sec：用于保护RPL免受DIO重放攻击的轻量级时间戳相关性

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3587977

Tahar Guerbouz;Akram Zine Eddine Boukhamla;Djalila Belkebir;Sahraoui Dhelim

{"title":"MVTC-Sec: Lightweight Timestamp Correlation for Securing RPL Against DIO Replay Attacks","authors":"Tahar Guerbouz;Akram Zine Eddine Boukhamla;Djalila Belkebir;Sahraoui Dhelim","doi":"10.1109/ACCESS.2025.3587977","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3587977","url":null,"abstract":"The rapid expansion of the Internet of Things (IoT) has brought greater attention to the reliability and security of communication within Low-Power and Lossy Networks (LLNs) with constrained resources. Of all the protocols for such networks, the Routing Protocol for Low-Power and Lossy Networks (RPL) plays a central role in enabling effective routing in 6LoWPAN-based IoT systems. However, RPL does not possess any built-in security measures, making it vulnerable to a wide range of attacks, primarily DODAG Information Object (DIO) message-based attacks such as DIO suppression, neighbor, and copycat attacks. Such attacks destabilize the network topology, reduce the packet delivery ratio (PDR), and increase both latency and energy consumption. To address these issues, this paper proposes MVTC-Sec, a Mathematically Validated Timestamp Correlation method that detects replay-based DIO attacks by analyzing deviations from the expected Trickle algorithm timing. Passively observing DIO intervals, MVTC-Sec identifies attack nodes violating the exponential backoff behavior, with efficient and lightweight attack detection irrespective of cryptographic overhead. We evaluate MVTC-Sec using the Cooja simulator under both static and mobile RPL scenarios, with varying attacker behaviors and replay intervals. Results show that MVTC-Sec achieves a detection accuracy ranging from 90% to 99%, improves packet delivery ratio (PDR) to 0.50-0.96, and reduces end-to-end latency by up to 60%. The scheme proves to be of low overhead, requiring only (48.1 kB ROM, 6.3 KB RAM), making it suitable for resource-constrained devices. Compared to the existing solutions, MVTC-Sec offers higher detection accuracy, lower complexity, and improved adaptability, making it an efficient and scalable protection method for RPL-based IoT networks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"122088-122106"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11077154","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646524","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}

引用次数: 0

A Survey of Holistic Approaches for Distributed Database Systems: From Conceptual Model to Deployment 分布式数据库系统整体方法综述：从概念模型到部署

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3587670

Gonçalo Carvalho;Jorge Bernardino;Bruno Cabral;Vasco Pereira

{"title":"A Survey of Holistic Approaches for Distributed Database Systems: From Conceptual Model to Deployment","authors":"Gonçalo Carvalho;Jorge Bernardino;Bruno Cabral;Vasco Pereira","doi":"10.1109/ACCESS.2025.3587670","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3587670","url":null,"abstract":"Database modeling defines the logical design, structure, and specifications for data storage and access within a DataBase Management System (DBMS), a core component of any Information System (IS). While conceptual database models (e.g., Entity-Relationship (ER) diagrams, Unified Modeling Language (UML)) facilitate the transition to physical models, they still fall short when it comes to supporting distributed and multi-layered architectures. Current approaches lack unified modeling abstractions, forcing manual reconciliation between high-level designs and their distributed implementations, leading to inefficiencies, deployment risks, and reliance on specialized teams. Existing tools (e.g., Kubernetes, Terraform) automate infrastructure but remain disconnected from Conceptual Models (CMs), requiring error-prone manual translation. This paper assesses the current state of the art in holistic approaches that aim to integrate modeling and deployment, identifies critical gaps in end-to-end automation, classifies the available deployment tools, and highlights advances that could enable building a distributed data management system based solely on its CM, potentially leading to greater agility and reduced operational complexity. Finally, the paper discusses open questions and research directions that indicate promising areas for future investigation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"120830-120851"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11077123","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646612","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}

引用次数: 0

Adapted Volt-VAr Extremum-Seeking Method for Voltage Regulation and Loss Minimization in Low Voltage Distribution Networks 低压配电网电压调节与损耗最小化的自适应v - var极值求法

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3586872

J. H. S. Carvalho;W. M. Dos Santos;A. R. Almeida;B. F. S. Júnior

{"title":"Adapted Volt-VAr Extremum-Seeking Method for Voltage Regulation and Loss Minimization in Low Voltage Distribution Networks","authors":"J. H. S. Carvalho;W. M. Dos Santos;A. R. Almeida;B. F. S. Júnior","doi":"10.1109/ACCESS.2025.3586872","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3586872","url":null,"abstract":"The high penetration of Distributed Generation (DG) in the low-voltage distribution grid has raised several concerns in recent years, mainly regarding overvoltage at the buses caused by the reversal of active power flow. In order to solve this problem, this work proposes an adaptation of the Volt-VAr Extremum-Seeking (Volt-Var-ES) method, which, in addition to promoting voltage regulation, also minimizes active losses in the network. This approach is framed within the concept of local Volt-VAr control since it requires only local measurements and does not depend on an accurate grid model. The IEEE European Low Voltage Test Feeder was used as the test network, with some adaptations to bring it closer to the Brazilian reality. The adapted method was applied in several allocation scenarios and at different levels of DG penetration, and its results were compared with those of the conventional Volt-VAr method, presented in IEEE 1547:2018. The simulations showed that the adapted Volt-VAr Extremum-Seeking method satisfactorily regulates the grid voltage and reduces active losses compared to the conventional Volt-VAr, generating financial savings for utilities and avoiding financial losses for photovoltaic (PV) system owners due to active power curtailment.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"121735-121747"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11075690","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646620","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}

引用次数: 0

MetaForecaster: A PSO-Driven Neural Model for Sustainable Industrial Air Quality Management MetaForecaster：可持续工业空气质量管理的pso驱动神经模型

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3587716

Marzia Ahmed;Shahrin Islam;Mohd Herwan Sulaiman;Md Maruf Hassan;Touhid Bhuiyan

{"title":"MetaForecaster: A PSO-Driven Neural Model for Sustainable Industrial Air Quality Management","authors":"Marzia Ahmed;Shahrin Islam;Mohd Herwan Sulaiman;Md Maruf Hassan;Touhid Bhuiyan","doi":"10.1109/ACCESS.2025.3587716","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3587716","url":null,"abstract":"Industrial carbon monoxide (CO) emissions significantly affect public health and environmental quality, necessitating advanced forecasting models for effective air quality management. Traditional neural network (NN)-based forecasting methods frequently exhibit limitations, including inadequate hyperparameter tuning and limited responsiveness to temporal variability in industrial emissions data. To address these challenges, this study proposes an optimized neural forecasting framework integrating Particle Swarm Optimization (PSO) with neural networks. The PSO algorithm strategically optimizes network weights and biases, utilizing the mean squared error (MSE) as the fitness metric to ensure prediction accuracy. The framework is validated using a segmented real-time dataset that distinguishes daytime and nighttime CO emissions, improving the adaptability and precision of the model. Comparative analyzes with established hybrid forecasting approaches, such as Genetic Algorithm-NN, Simulated Annealing-NN, and Differential Evolution-NN, demonstrate the superior performance of the proposed PSO-NN model, achieving notably low prediction errors (MSE: <inline-formula> <tex-math>$1.1941 times 10^{-7}$ </tex-math></inline-formula>), MAPE: 0.0016 and a high coefficient of determination (<inline-formula> <tex-math>$R^{2}$ </tex-math></inline-formula>: 0.99999). Furthermore, Theil’s U statistic confirms the robustness and predictive reliability of the model. Consequently, the proposed PSO-NN framework emerges as an effective real-time decision support system, facilitating sustainable air quality governance and promoting environmentally responsible industrial production practices.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"121670-121685"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11077164","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646621","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}

引用次数: 0

A Novel Closed-Loop Deep Learning-Based Smart Infusion Rate Monitoring Technique for Safe Intravenous Medication Administration 一种基于闭环深度学习的安全静脉给药智能输液速率监测技术

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3587531

Subrata Bhattacharjee;Gun Ho Kim;Hongje Lee;Kyoung Won Nam

{"title":"A Novel Closed-Loop Deep Learning-Based Smart Infusion Rate Monitoring Technique for Safe Intravenous Medication Administration","authors":"Subrata Bhattacharjee;Gun Ho Kim;Hongje Lee;Kyoung Won Nam","doi":"10.1109/ACCESS.2025.3587531","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3587531","url":null,"abstract":"Medication administration via an intravenous (IV) catheter is a widely used medical procedure; however, incidents related to IV administration have consistently been reported to regulatory agencies. To improve patient safety during these incidents, it is essential to enhance the monitoring of IV administration. This study proposes an artificial intelligence-based technique for real-time infusion rate (IR) monitoring that automates several processes: the initial setup for image monitoring, the monitoring of variations in in-bag liquid volume and infusion pump settings, the determination of the relevance between infusion status and in-bag liquid residue, and the alarm processes for early detection of IV administration-related emergencies, using deep learning models and mathematical estimations. The experimental results demonstrate that the average error rate for estimating in-bag liquid volume is less than 5.00%, the average mismatch between the bag-extracted IR and the pump-extracted IR is under 3.00%, the average error rate for the “time-to-bag-empty” alarm is below 6.00%, and the error rate for the “low in-bag liquid volume” alarm is under 10.00%. The accuracy of detecting abnormal IR settings of the infusion pump was 100%. Based on these results, we conclude that the proposed artificial intelligence-based smart IR status monitoring technique shows promise as a prototype for autonomous IV administration monitoring with minimal human intervention, serving as a foundational step toward clinically deployable solutions in future healthcare settings.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"120603-120618"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11075678","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646656","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}

引用次数: 0

Data-Driven Optimization of Aspect Ratio in Permanent Magnet Machines Using Deep Learning and SHAP Analysis 基于深度学习和SHAP分析的永磁体宽高比数据驱动优化

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-10 DOI: 10.1109/ACCESS.2025.3586216

Kyeong Jin Kim;Ji Hoon Park;Dong Hoo Min;Seun Guy Min

{"title":"Data-Driven Optimization of Aspect Ratio in Permanent Magnet Machines Using Deep Learning and SHAP Analysis","authors":"Kyeong Jin Kim;Ji Hoon Park;Dong Hoo Min;Seun Guy Min","doi":"10.1109/ACCESS.2025.3586216","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3586216","url":null,"abstract":"The aspect ratio, defined as the ratio of the outer diameter to the stack length, is a critical parameter in permanent magnet (PM) machine design, with a profound impact on motor performance. This study presents a novel framework integrating deep learning and Shapley additive explanations (SHAP) to analyze the influence of design variables on the optimal aspect ratio. To achieve this, extensive datasets are generated using a metaheuristic optimization algorithm, covering diverse scenarios and objectives to ensure robust generalization and accuracy. A deep learning model is then trained on these datasets to capture the complex, nonlinear relationships between design variables and the aspect ratio. To enhance the interpretability of the “opaque model”, SHAP is employed, providing a detailed attribution analysis of each design variable contribution to the aspect ratio. This dual approach successfully uncovers the complex relationships between the aspect ratio and design variables across diverse design scenarios, thereby enabling actionable guidelines for sizing the outer diameter and height of the motor in the early design phase. Furthermore, the proposed methodology offers a scalable framework for analyzing other key ratios in motor design, establishing itself as a foundational tool for future advancements in this field.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"122164-122174"},"PeriodicalIF":3.4,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11075776","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144646641","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}

引用次数: 0