检索结果-内蒙古大学图书馆

IEEE Open Journal of Industry Applications 2025年 6卷 178-190页

作者： Kritprajun, Paychuda Tolbert, Leon M. Sutton, Elizabeth Liu, Yunting Wang, Jingxin Praisuwanna, Nattapat Ferrari, Maximiliano University of Tennessee Department of Electrical Engineering and Computer Science KnoxvilleTN37996 United States The Pennsylvania State University Department of Electrical Engineering University ParkPA16802 United States Oak Ridge National Laboratory Grid Systems Architecture Group Oak RidgeTN37830 United States

As the utilization of supercapacitors in power system applications continues to increase, it is important to observe their behavior under transient and long-term operations to understand their impact on power grids. A real-time reconfigurable hardware testbed (HTB) is a power network emulator that provides flexibility in studying various power system scenarios. This work presents an emulation of a supercapacitor for a photovoltaic (PV) system on the HTB platform such that its dynamic behavior during power system scenarios can be observed. The developed emulator on the HTB is verified by comparing the emulation results with the model developed in MATLAB/Simulink. An improvement of grid frequency support control is proposed to enable fast-frequency recovery service provided by a grid-connected PV with SC system (PVSS). The experimental results of the emulator are consistent with the simulation results under grid support scenarios. This supercapacitor emulator can potentially be used for various power system scenarios supporting other research in addition to the PV applications presented in this paper. © 2020 IEEE.

关键词： Electric power transmission networks

来源：评论

学校读者我要写书评

暂无评论

Nucleus segmentation from the histopathological images of liver cancer through an efficient deep learning framework

引用

Multimedia Tools and Applications 2025年第8期84卷 5025-5050页

作者： Sunesh Tripathi, Jyoti Saini, Anu Tiwari, Sunita Kumari, Sunita Taqui, Syed Noeman Almoallim, Hesham S. Alharbi, Sulaiman Ali Raghavan, S.S. Department of Information Technology MSIT Janakpuri New Delhi110058 India Department of Computer Science and Engineering G. B. Pant DSEU Okhla I Campus New Delhi110020 India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai602105 India Department of Oral and Maxillofacial Surgery College of Dentistry King Saud University Riyadh11545 Saudi Arabia Department of Botany and Microbiology College of Science King Saud University Riyadh11451 Saudi Arabia Department of Biology University of Tennessee Health Science Center MemphisTN United States

Segmenting nuclei in histopathological images presents challenges due to variable sizes and overlapping regions, compounded by inter-class heterogeneity in shape and function. To overcome these, we proposed a robust deep learning architecture integrated with a novel edge detection technique based on local standard deviation. This method efficiently identifies nuclei edges, even at Multiscale levels, by exploiting the relationship between local standard deviation and image features. Our CNN architecture consists of stable residual, bottleneck, and attention decoding blocks, enabling effective extraction of high-level semantics and precise image localization. Evaluation on H&E stained liver disease histopathological images and a multi-organ database showcases the effectiveness of our approach, comparable to modern deep neural networks. Three performance indicators are computed to statistically assess segmentation efficacy, consistently demonstrating the superiority of our method over others. For multi-organ dataset segmentation using proposed methods attains the Jaccard index (89.99%), Precision (91.5%), Recall (91.1%), F1-measure (91.27%), and Accuracy (95.42%). Similarly for liver dataset attains Jaccard index (65.72%), Precision (88.74%), Recall (89.53%), F1-measure (90.12%), and Accuracy (94.85%). By addressing the limitations of previous unsupervised methods, our approach offers a robust solution for nuclei segmentation across diverse datasets. The significance of our work lies in its potential to enhance automated nuclei recognition in medical diagnosis and research, facilitating more accurate analysis of histopathological images and ultimately contributing to improved patient care and understanding of disease pathology. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Virtual MOLLI Target: Generative Adversarial Networks Toward Improved Motion Correction in MRI Myocardial T1 Mapping

引用

Journal of Magnetic Resonance Imaging 2025年第1期61卷 209-219页

作者： Pan, Nai-Yu Huang, Teng-Yi Yu, Jui-Jung Peng, Hsu-Hsia Chuang, Tzu-Chao Lin, Yi-Ru Chung, Hsiao-Wen Wu, Ming-Ting Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Biomedical Engineering and Environmental Sciences National Tsing Hua University Hsinchu Taiwan Department of Electrical Engineering National Sun Yat-Sen University Kaohsiung Taiwan Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan Department of Radiology Kaohsiung Veterans General Hospital Kaohsiung Taiwan School of Medicine College of Medicine National Yang Ming Chiao Tung University Taipei Taiwan

Background: The modified Look-Locker inversion recovery (MOLLI) sequence is commonly used for myocardial T1 mapping. However, it acquires images with different inversion times, which causes difficulty in motion correction for respiratory-induced misregistration to a given target image. Hypothesis: Using a generative adversarial network (GAN) to produce virtual MOLLI images with consistent heart positions can reduce respiratory-induced misregistration of MOLLI datasets. Study Type: Retrospective. Population: 1071 MOLLI datasets from 392 human participants. Field Strength/Sequence: Modified Look-Locker inversion recovery sequence at 3 T. Assessment: A GAN model with a single inversion time image as input was trained to generate virtual MOLLI target (VMT) images at different inversion times which were subsequently used in an image registration algorithm. Four VMT models were investigated and the best performing model compared with the standard vendor-provided motion correction (MOCO) technique. Statistical Tests: The effectiveness of the motion correction technique was assessed using the fitting quality index (FQI), mutual information (MI), and Dice coefficients of motion-corrected images, plus subjective quality evaluation of T1 maps by three independent readers using Likert score. Wilcoxon signed-rank test with Bonferroni correction for multiple comparison. Significance levels were defined as P < 0.01 for highly significant differences and P < 0.05 for significant differences. Results: The best performing VMT model with iterative registration demonstrated significantly better performance (FQI 0.88 ± 0.03, MI 1.78 ± 0.20, Dice 0.84 ± 0.23, quality score 2.26 ± 0.95) compared to other approaches, including the vendor-provided MOCO method (FQI 0.86 ± 0.04, MI 1.69 ± 0.25, Dice 0.80 ± 0.27, quality score 2.16 ± 1.01). Data Conclusion: Our GAN model generating VMT images improved motion correction, which may assist reliable T1 mapping in the presence of respiratory motion

关键词： generative adversarial networks MOLLI registration

来源：评论

学校读者我要写书评

暂无评论

A Framework for Video Based Sign Language Interpretation Using Machine Learning and Statistical Methods

A Framework for Video Based Sign Language Interpretation Usi...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Swathi D Susmetha K Sreeji. S S. Mangairkarasi B.E Computer Science and Engineering with Data Science Sathyabama Institute of Science and Technology Semmancheri Chennai TamilNadu India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Semmancheri Chennai TamilNadu India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The Sign Language Recognition System has been designed to capture video input, process it to detect hand gestures, and translate these gestures into readable text. The project consists of several key components and steps: Video Processing: Using OpenCV, the system captures frames from the video input. MediaPipe processes these frames to detect and track hand landmarks in real time. OpenCV capabilities allow for efficient frame extraction and basic image processing tasks such as resizing and normalization. Hand Detection and Tracking: MediaPipe pre-trained models identify and track hand movements within the video frames. The accurate detection and tracking of the hand movements are critical for the subsequent recognition of the sign language gestures. Sign Language Recognition: The core system is the deep learning model, trained using the TensorFlow and Keras on a dataset of sign language gestures. The model learns to classify the detected hand movements into corresponding sign language characters or words. Convolutional Neural Networks (CNNs) are typically used for task due to their effectiveness in image recognition tasks. Text Display: Once the system recognizes the signs, it converts them into text and displays the output. This can be done through a console output or a graphical user interface (GUI) built with Tkinter. The GUI provides a user friendly experience, allowing users to see the translated text in real-time.

关键词： Hands Deep learning Sign language Translation Tracking Text recognition Speech recognition Streaming media Real-time systems Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Towards More Accurate Personalized Image Generation: Addressing Overfitting and Evaluation Bias

arXiv

引用

arXiv 2025年

作者： Li, Mingxiao Qu, Tingyu Tuytelaars, Tinne Moens, Marie-Francine Department of Computer Science KU Leuven Belgium Department of Electrical Engineering KU Leuven Belgium

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a user-provided subject while maintaining both consistency of the subject and flexibility to accommodate various textual descriptions of that subject. However, current methods face challenges in ensuring fidelity to the text prompt while not overfitting to the training data. In this work, we introduce a novel training pipeline that incorporates an attractor to filter out distractions in training images, allowing the model to focus on learning an effective representation of the personalized subject. Moreover, current evaluation methods struggle due to the lack of a dedicated test set. The evaluation set-up typically relies on the training data of the personalization task to compute text-image and image-image similarity scores, which, while useful, tend to overestimate performance. Although human evaluations are commonly used as an alternative, they often suffer from bias and inconsistency. To address these issues, we curate a diverse and high-quality test set with well-designed prompts. With this new benchmark, automatic evaluation metrics can reliably assess model performance.1 © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Feasibility Analysis Study on Constructing a Grid Intrusion Detection System Using Semi-supervised Learning Models 2nd

Feasibility Analysis Study on Constructing a Grid Intrusion ...

引用

2nd International Conference on Security and Information Technologies with AI, Internet Computing and Big-data Applications, SITAIBA 2023

作者： Tsai, Chia-Wei Lin, Jason Yang, Chun-Wei Loo, Fu-Nie Department of Computer Science and Information Engineering National Taichung University of Science and Technology No.129 Sec.3 Sanmin Rd North District Taichung404 Taiwan Department of Computer Science and Engineering National Chung Hsing University No. 145 Xingda Rd. South District Taichung40227 Taiwan Master Program for Digital Health Innovation China Medical University No. 100 Sec. 1 Jingmao Rd. Beitun Dist. Taichung406040 Taiwan

ISBN: (纸本)9789819777853

In recent years, due to the proliferation of information and communication technology, as well as AI technology, industrial control systems, which were once in a closed network environment, have also integrated related technologies and gradually connected to external networks. Although this can enhance the efficiency of industrial production, it greatly increases the information security threats to industrial control systems. Among them, the information security issues of critical infrastructures are a key issue. If these critical infrastructures are attacked by cyber hackers, it could pose threats that jeopardize the safety of the general population. In light of this, this study focuses on the critical infrastructure of the power grid, proposing a semi-supervised intrusion detection system (IDS) technology by using the one-class classification. It analyzes data from the electricity distribution system to assess whether the system has been attacked. This research employs a power grid dataset to train the proposed model and execute the experiments. The experimental results demonstrate the feasibility of the proposed method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Scheduling for Oil Spill SAR Image Detection in Space-Air-Ground Integrated Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Son, Seok Bin Park, Soohyun Korea University Department of Electrical and Computer Engineering Seoul02841 Korea Republic of Sookmyung Women's University Division of Computer Science Seoul04310 Korea Republic of

Oil spills represent significant environmental hazards in ocean ecosystems, requiring rapid and accurate detection and response mechanisms. Due to its efficacy, synthetic aperture radar (SAR) is an important tool for remote monitoring of ocean environments. However, operational constraints such as communication time between low Earth orbit (LEO) satellites and ground stations (GS), as well as finite buffers, pose challenges. To address these issues, this paper proposes a space-air-ground-integrated network (SAGIN) scenario comprising LEO satellites, high altitude platforms (HAPs), and ground stations (GSs), suitable for rapid and accurate oil spill detection using SAR images. In addition, a novel three-step algorithm is proposed to facilitate SAR image transmission effectively. The first step of the proposed algorithm focuses on maximizing the transmission of ocean SAR images from the LEO satellites to the HAPs. This optimization involves the neural Myerson auction (NMA)-based scheduler, a second-price auction mechanism with deep learning methodologies for truthfulness, distributed computation, and low computational complexity. In addition, the pathloss is also considered for effective communication system design. The second step algorithm aims to maximize data transmission efficiency from HAPs to GSs, employing scheduling strategies based on the Markov decision process (MDP). This algorithm enables optimal decision-making over time steps, considering the throughput of each GS and the age of the information (AoI) ratio. Finally, an image compression rate control algorithm based on Lyapunov optimization is employed at the GSs to enhance detection accuracy while ensuring queue stability. The performance of the proposed three-step algorithm is intensively evaluated against various benchmark algorithms, demonstrating its superiority in oil spill detection efficacy. © 1967-2012 IEEE.

关键词： Oil spills

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithm;for Conversion Predictors of Clinically Isolated Syndrome (CIS) to Multiple Sclerosis (MS)

Comparative Analysis of Machine Learning Algorithm;for Conve...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Serena Mendanha Keerthi Reddy Gudibandi Koduru Hajarathaiah Bharat Reddy Gudibandi Murali Krishna Enduri School of Computer Science and Engineering VIT-AP University Amaravati India School of Electronics Engineering VIT-AP University Amaravati India Department of Computer Science and Engineering SRM University AP India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The central nervous system is impacted by multiple sclerosis (MS), a chronic neurological condition that causes significant cognitive and physical deficits. Better disease management and prompt intervention depend on early and precise detection. Effective diagnosis of MS is hampered by a number of factors, such as small datasets, significant clinical presentation variability, difficult feature selection, model generalization problems, and integration of multimodal data such as magnetic resonance imaging and genetic markers. Several machine learning (ML) models are assessed in this study in order to predict the development of clinically isolated syndrome (CIS) to multiple sclerosis. Using clinical and magnetic resonance data from patients with CIS at risk of developing MS, we evaluate the effectiveness of support vector machines (SVM), K nearest neighbor (KNN), decision trees (DT), random forests (RF), logistic regression (LR), Gaussian naive Bayes (Gaussian NB) and XGBoost (XG). Evaluation is performed using performance criteria including F1 score, recall, precision, and precision. According to our research, Random Forest has the best prediction accuracy, which makes it a potentially useful tool for helping doctors diagnose and treat MS patients early. Notwithstanding these developments, issues like model interpretability and data scarcity still exist. In order to improve diagnosis precision, future research will concentrate on enhancing these models by integrating deep learning methods, genetic markers,, and more advanced imaging modalities.

关键词： Support vector machines Deep learning Radio frequency Sentiment analysis Multiple sclerosis Machine learning algorithms Predictive models Genetics Data models Random forests

来源：评论

学校读者我要写书评

暂无评论

MWRS: A MAB-based Worker Recruitment Scheme with Tripartite Stackelberg Game for Reliable Mobile Crowdsensing

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ouyang, Yan Zeng, Feng Xiong, Neal N. Liu, Anfeng Pedrycz, Witold School of Computer Science and Engineering Central South University Changsha410083 China Department of Computer Science and Mathematics Sul Ross State University AlpineTX79830 United States Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Faculty of Engineering and Natural Sciences Department of Computer Engineering Istinye University Istanbul Turkey Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

Mobile Crowdsensing (MCS) has emerged as a compelling paradigm for data sensing and collection, leveraging the widespread adoption of mobile devices and the active participation of numerous users. Despite its potential, MCS faces critical challenges, particularly in recruiting reliable workers and acquiring high-quality sensing data. Most existing approaches assume prior information on worker quality and are vulnerable to collusion attacks, especially having not comprehensively considered workers' reliability and stability. To address these problems, we propose a Multi-Armed Bandit (MAB) based Worker Recruitment Scheme (MWRS) integrated with the Tripartite Stackelberg Game (TSG) for MCS. Specifically, a trust evaluation and truth inference mechanism is introduced to assess the trustworthiness of workers through active truth detection. To enhance recruitment quality, we employ a trust-aware worker selection mechanism that utilizes a modified Upper Confidence Bound (UCB) algorithm, achieving an optimal balance between exploration and exploitation. Furthermore, the interactions among participants are modeled using a TSG framework, which formulates their respective payoffs to determine optimal decision-making strategies, thus achieving mutually beneficial outcomes. Extensive evaluations on real-world datasets demonstrate that our proposed scheme improves total quality by up to 30.8% and reduces regret by up to 80.3% compared to existing methods. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Distributed Computation Offloading in Vehicular Edge Networks Using Proactive Service Reservations and Multi-Agent Learning

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Shivanna, Veena Srikanth, Aadithya Tumuluru, Vamsi Krishna RV University School of Computer Science and Engineering Bengaluru India PES University Department of Electronics and Communication Engineering Bengaluru India

Future vehicular edge computing (VEC) networks are projected to generate massive amounts of computation tasks which exhibit dynamic spatio-temporal heterogeneity. Vehicular users will greatly benefit if the VEC network provides the following information a priori: a) estimates of the delays along the paths and b) amounts of network resources that will be assigned. Existing works did not provide such prior information and only dealt with real-time computation offloading. In this paper, we propose a novel distributed computation offloading strategy in which the vehicular users independently make proactive service reservations across the road side units (RSUs) along their paths. Such reservations are based on the computation offloading delays reported by the RSUs. These delays depend on the optimal network resources assigned by the RSUs to the vehicular users over different reservation slots. In order to determine the optimal assignment of network resources, we propose a new multi-agent deep reinforcement learning (MADRL) problem where the RSUs act as agents. The objective of the MADRL problem is to maximize the mean number of offloaded tasks. This objective is found as the outcome of the proactive service reservation problem solved by each vehicular user when it is injected into the VEC network. The MADRL problem is approximated using a centralized-critic-distributed-actors model. The proactive service reservation introduces time coupling in the calculation of the rewards, therefore a novel training algorithm is proposed for solving the MADRL problem. Compared to some benchmark real-time computation offloading schemes, the proposed work benefited the vehicular users significantly by providing prior estimates of the delays along their paths. Specifically, the percentage of offloaded tasks achieving the highest utility was 14-20 % higher, b) the computation offloading delays experienced by the vehicular users along the path were the lowest, and c) the utilization of netw

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：