检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Tao Bian, Zilin Lei, Haozhe Zuo, Fan Yang, Ya-Ting Zhu, Quanyan Li, Zhenning Chen, Zhibin Ozbay, Kaan Department of Electrical and Computer Engineering New York University United States Department of Civil and Urban Engineering New York University United States State Key Laboratory of Internet of Things for Smart City University of Macau China Shanghai Key Laboratory of Urban Design and Urban Science NYU Shanghai China

Traditional mobility management strategies emphasize macro-level mobility oversight from traffic-sensing infrastructures, often overlooking safety risks that directly affect road users. To address this, we propose a Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics (DT-DIMA) system. The DT-DIMA system introduces four novel services that extract real-time traffic information from pan-tilt-cameras (PTCs), synchronize this data into a digital twin to accurately replicate the physical world, and predict network-wide mobility and safety risks in real time. The system’s innovation lies in its integration of advanced machine learning, simulation, and online control modules, including Spatial-Temporal Traffic Estimation (STTE) for real-time traffic data fusion and prediction, Mesoscopic Traffic Safety Simulation (MTSS) for real-time safety risk prediction, and Risk-Constrained Correlated Online Learning (RiCCOL) for real-time PTC control. Tested and evaluated under normal traffic conditions and incidental situations (e.g., unexpected accidents, pre-planned work zones) in a simulated testbed in Brooklyn, New York, DT-DIMA demonstrated mean absolute percentage errors (MAPEs) ranging from 8.40% to 15.11% in estimating network-level traffic volume and MAPEs from 0.85% to 12.97% in network-level safety risk prediction. In addition, the highly accurate safety risk prediction enables PTCs to preemptively monitor road segments with high driving risks before incidents take place. Such proactive PTC surveillance creates around a 5-minute lead time in capturing traffic incidents. The DT-DIMA system enables transportation managers to understand mobility not only in terms of traffic patterns but also driver-experienced safety risks, allowing for proactive resource allocation in response to various traffic situations. To the authors’ best knowledge, DT-DIMA is the first urban mobility management system that considers both mobility and safety risks based on digital twin

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Ultrasound Image Denoiser Using Parallel Attention Modules and Capsule Generative Adversarial Network

引用

Informatics in Medicine Unlocked 2024年 50卷

作者： Sivaanpu, Anparasy Punithakumar, Kumaradevan Thanikasalam, Kokul Noga, Michelle Zheng, Rui Ta, Dean Lou, Edmond H.M. Le, Lawrence H. Department of Radiology and Diagnostic Imaging University of Alberta Edmonton Alberta Canada Department of Computer Science University of Jaffna Jaffna Sri Lanka School of Information Science and Technology ShanghaiTech University Shanghai 201210 China Department of Biomedical Engineering School of Information Science and Technology Fudan University Shanghai China Department of Electrical and Computer Engineering University of Alberta Edmonton Alberta Canada State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China

The quality of ultrasound (US) imaging has been constrained by its limited contrast and resolution, inherent speckle noise, and the presence of other artifacts. Existing traditional and deep learning-based US denoising approaches have many limitations, such as reliance on manual parameter configurations, poor performance for unknown noise levels, the requirement for a large number of training data, and high computational expense. To address these challenges, we propose a novel Generative Adversarial Network (GAN) based denoiser. Capsule networks are utilized in both the generator and discriminator of the proposed GAN to capture intricate sparse features with less complexity. In addition, bias components are removed from all neurons of the generator to handle the unknown noise levels. A parallel attention module is also included in the proposed model to further enhance denoising performance. The proposed approach is trained in a semi-supervised manner and can thus be trained with fewer labeled images. Experimental evaluation on publicly available HC18 and BUSI datasets showed that the proposed approach achieved state-of-the-art denoising performance, with PSNR values of 33.86 and 34.16, and SSIM indices of 0.91 and 0.90, respectively. Moreover, experiments showed that the proposed approach is lightweight and more than twice as fast as similar denoisers. © 2024

关键词： Capsule Network Generative Adversarial Network Image denoising Semi-supervision Ultrasound image

来源：评论

学校读者我要写书评

暂无评论

Federated Optimization of Smooth Loss Functions

arXiv

引用

arXiv 2022年

作者： Jadbabaie, Ali Makur, Anuran Shah, Devavrat The Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Computer Science The Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States

In this work, we study empirical risk minimization (ERM) within a federated learning framework, where a central server seeks to minimize an ERM objective function using n samples of training data that is stored across m clients and the server. The recent flurry of research in this area has identified the Federated Averaging (FedAve) algorithm as the staple for determining ϵ-approximate solutions to the ERM problem. Similar to standard optimization algorithms, e.g., stochastic gradient descent, the convergence analysis of FedAve and its variants only relies on smoothness of the loss function in the optimization parameter. However, loss functions are often very smooth in the training data too. To exploit this additional smoothness in data in a federated learning context, we propose the Federated Low Rank Gradient Descent (FedLRGD) algorithm. Since smoothness in data induces an approximate low rank structure on the gradient of the loss function, our algorithm first performs a few rounds of communication between the server and clients to learn weights that the server can use to approximate clients' gradients using its own gradients. Then, our algorithm solves the ERM problem at the server using an inexact gradient descent method. To theoretically demonstrate that FedLRGD can have superior performance to FedAve, we present a notion of federated oracle complexity as a counterpart to canonical oracle complexity in the optimization literature. Under some assumptions on the loss function, e.g., strong convexity and smoothness in the parameter, η-Hölder class smoothness in the data, etc., we prove that the federated oracle complexity of FedLRGD scales like (Equation presented) and that of FedAve scales like (Equation presented) (neglecting typically sub-dominant factors), where 1 is the ratio of client-to-server communication time to gradient computation time, p is the parameter dimension, and d is the data dimension. Then, we show that when d is small compared to n and the l

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Label-Free Virtual HER2 Immunohistochemical Staining of Breast Tissue using Deep Learning

引用

Biomedical engineering Frontiers 2022年第1期3卷 422-436页

作者： Bijie Bai Hongda Wang Yuzhu Li Kevin de Haan Francesco Colonnese Yujie Wan Jingyi Zuo Ngan B.Doan Xiaoran Zhang Yijie Zhang Jingxi Li Xilin Yang Wenjie Dong Morgan Angus Darrow Elham Kamangar Han Sung Lee Yair Rivenson Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCA 90095USA Bioengineering Department University of CaliforniaLos Angeles 90095USA California NanoSystems Institute(CNSI) University of CaliforniaLos AngelesCAUSA Computer Science Department University of CaliforniaLos AngelesCAUSA Physics and Astronomy Department University of CaliforniaLos AngelesCA 90095USA Translational Pathology Core Laboratory University of CaliforniaLos AngelesCA 90095USA Statistics Department University of CaliforniaLos AngelesCA 90095USA Department of Pathology and Laboratory Medicine University of California at DavisSacramentoCA 95817USA Department of Surgery University of CaliforniaLos AngelesCA 90095USA

The immunohistochemical(IHC)staining of the human epidermal growth factor receptor 2(HER2)biomarker is widely practiced in breast tissue analysis,preclinical studies,and diagnostic decisions,guiding cancer treatment and investigation of ***2 staining demands laborious tissue treatment and chemical processing performed by a histotechnologist,which typically takes one day to prepare in a laboratory,increasing analysis time and associated ***,we describe a deep learning-based virtual HER2 IHC staining method using a conditional generative adversarial network that is trained to rapidly transform autofluorescence microscopic images of unlabeled/label-free breast tissue sections into bright-field equivalent microscopic images,matching the standard HER2 IHC staining that is chemically performed on the same tissue *** efficacy of this virtual HER2 staining framework was demonstrated by quantitative analysis,in which three board-certified breast pathologists blindly graded the HER2 scores of virtually stained and immunohistochemically stained HER2 whole slide images(WSIs)to reveal that the HER2 scores determined by inspecting virtual IHC images are as accurate as their immunohistochemically stained counterparts.A second quantitative blinded study performed by the same diagnosticians further revealed that the virtually stained HER2 images exhibit a comparable staining quality in the level of nuclear detail,membrane clearness,and absence of staining artifacts with respect to their immunohistochemically stained *** virtual HER2 staining framework bypasses the costly,laborious,and time-consuming IHC staining procedures in laboratory and can be extended to other types of biomarkers to accelerate the IHC tissue staining used in life sciences and biomedical workflow.

关键词： HER2 consuming Deep

来源：评论

学校读者我要写书评

暂无评论

Roles of UAVs, Robots, and AI in Earthquake Disaster Management 7

Roles of UAVs, Robots, and AI in Earthquake Disaster Managem...

引用

7th International Youth Conference on Radio Electronics, electrical and Power engineering, REEPE 2025

作者： Abdalzaher, Mohamed S. Shaaban, Mostafa Krichen, Moez Aburukba, Raafat American University of Sharjah Electrical Engineering Department Sharjah United Arab Emirates National Research Institute of Astronomy and Geophysics Seismology Department Cairo Egypt Energy Water and Sustainable Environment Research Center American University of Sharjah United Arab Emirates Al-Baha University Al-Baha Saudi Arabia ReDCAD Laboratory University of Sfax Sfax Tunisia American University of Sharjah Computer Science and Engineering Department Sharjah United Arab Emirates

ISBN: (纸本)9798331531836

Earthquakes are among the most destructive natural disasters, causing widespread loss of life, property, and infrastructure. Effective disaster management is essential to minimize their impact. This article examines the critical roles of Unmanned Aerial Vehicles (UAVs), robots, and Artificial Intelligence (AI) in earthquake disaster management across the phases of pre-disaster preparedness, real-time response, during the event, and after the disaster. The paper explores various types of UAVs and robots utilized for earthquake monitoring, highlights their advantages, and addresses the challenges associated with their deployment. Besides, the types of robots are also addressed to contribute to earthquake disaster management and to alleviating the consequences. By leveraging these advanced technologies, disaster response and recovery efforts can be significantly enhanced, offering new possibilities for resilience and efficiency in managing earthquake-related emergencies. © 2025 IEEE.

关键词： Artificial Intelligence Disaster Management Earthquake Robots UAVs

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pricing based Near-Optimal Resource Allocation for Elastic Edge Offloading

引用

IEEE Transactions on Mobile Computing 2025年

作者： Xia, Yun Xue, Hai Zhang, Di Mumtaz, Shahid Xu, Xiaolong Rodrigues, Joel J. P. C. University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Zhengzhou University School of Electrical and Information Engineering Henan International Joint Laboratory of Intelligent Health Information System National Telemedicine Center National Engineering Laboratory for Internet Medical Systems and Applications Zhengzhou450001 China Nottingham Trent University Department of Engineering NottinghamNG1 4FQ United Kingdom Kyung Hee University Department of Electronic Engineering Gyeonggi-do Yongin-si17104 Korea Republic of Nanjing University of Information Science and Technology School of Software Nanjing210044 China Amazonas State University Manaus Brazil

In mobile edge computing (MEC), task offloading can significantly reduce task execution latency and energy consumption of end user (EU). However, edge server (ES) resources are limited, necessitating efficient allocation to ensure the sustainable and healthy development for MEC system. In this paper, we propose a dynamic pricing mechanism based near-optimal resource allocation for elastic edge offloading. First, we construct a resource pricing model and accordingly develop the utility functions for both EU and ES, the optimal pricing model parameters are derived by optimizing the utility functions. In the meantime, our theoretical analysis reveals that the EU's utility function reaches a local maximum within the search range, but exhibits barely growth with increased resource allocation beyond this point. To this end, we further propose the Dynamic Inertia and Speed-Constrained particle swarm optimization (DISC-PSO) algorithm, which efficiently identifies the near-optimal resource allocation. Comprehensive simulation results validate the effectiveness of DISC-PSO algorithm, demonstrating that it significantly outperforms existing schemes by reducing the average number of iterations to reach a near-optimal solution by 86.88%, increasing the EU utility function value by 0.13%, and decreasing the variance of results by 96.78%. © 2025 IEEE. All rights reserved.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Autonomous control management of synchronous generators in microgrid system

Autonomous control management of synchronous generators in m...

引用

International Conference on Energy, Power, Environment, Control and Computing (ICEPECC 2025)

作者： Hafiz Ghulam Murtza Qamar Adil Ashraf Fareed Ahmad Ayesha Riaz Muhammad Imran Muhammad Zain Yousaf Imran Khan School of Electrical Engineering Yanshan University Qinhuangdao 066004 People's Republic of China Department of Electrical Electronics and Computer Systems University of Sargodha People's Republic of China Center for Renewable Energy and Microgrids Huanjiang Laboratory Zhejiang University Zhuji Zhejiang 311816 People's Republic of China

ISBN: (数字)9781837243150

Decentralized excitation control based on local asynchronous clock feedback measurement leads to the problem of decentralized incompatibility of excitation controllers, which reduces the ability of excitation control design to improve the stability of power systems. Therefore, the problem of decentralized compatible excitation control is proposed, and the effect of excitation control on the dynamic characteristics of the system under compatible and incompatible modes is compared and analyzed, and the shortcomings of decentralized incompatible excitation control and the advantages of decentralized compatible excitation control are given.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Probabilistic Semantic Communication over Space-Air-Ground Integrated Networks

arXiv

引用

arXiv 2024年

作者： Zhao, Zhouxiang Yang, Zhaohui Chen, Mingzhe Zhang, Zhaoyang Xu, Wei Huang, Kaibin College of Information Science and Electronic Engineering Zhejiang University China Hangzhou310027 China Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States National Mobile Communications Research Laboratory Southeast University Nanjing211189 China The Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

Space-air-ground integrated networks (SAGINs) are emerging as a pivotal element in the evolution of future wireless networks. Despite their potential, the joint design of communication and computation within SAGINs remains a formidable challenge. In this paper, the problem of energy efficiency in SAGIN-enabled probabilistic semantic communication (PSC) system is investigated. In the considered model, a satellite needs to transmit data to multiple ground terminals (GTs) via an unmanned aerial vehicle (UAV) acting as a relay. During transmission, the satellite and the UAV can use PSC technique to compress the transmitting data, while the GTs can automatically recover the missing information. The PSC is underpinned by shared probability graphs that serve as a common knowledge base among the transceivers, allowing for resource-saving communication at the expense of increased computation resource. Through analysis, the computation overhead function in PSC is a piecewise function with respect to the semantic compression ratio. Therefore, it is important to make a balance between communication and computation to achieve optimal energy efficiency. The joint communication and computation problem is formulated as an optimization problem aiming to minimize the total communication and computation energy consumption of the network under latency, power, computation capacity, bandwidth, semantic compression ratio, and UAV location constraints. To solve this non-convex non-smooth problem, we propose an iterative algorithm where the closed-form solutions for computation capacity allocation and UAV altitude are obtained at each iteration. Numerical results show the effectiveness of the proposed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Design of A 50-kW Medium Frequency Medium Voltage Transformer for 10-kV SiC-Based Dual Active Bridge Converter

Design of A 50-kW Medium Frequency Medium Voltage Transforme...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Zihan Gao Dingrui Li Ruirui Chen Hua Bai Leon Tolbert Fred Wang Min H. Kao Department of Electrical Engineering and Computer Science The University of Tennessee Knoxville Knoxville TN USA Oak Ridge National Laboratory Oak Ridge TN USA

In this paper, a 50-kW 1-kV/6.25-kV medium voltage dual-active-bridge (DAB) transformer has been designed and tested. The shell-type transformer structure with stacked small cores is selected to integrate the leakage inductance and reduce the eddy current loss. Dry-type insulation with selective shielding is adopted and both winding-to-ground and winding turn-to-turn insulation are considered. The transformer geometry-based design procedure is discussed to achieve high efficiency and power density considering the effect of eddy current loss and insulation constraint. Tests up to the full voltage and power were performed and the DAB transformer achieved 99.66% full-load efficiency and 13.5 kW/L density for the transformer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Methods for Kernel Initialization of Convolutional Neural Network Model Applied to Plant Disease Classification

Adaptive Methods for Kernel Initialization of Convolutional ...

引用

electrical, Electronic and Information sciences (eStream), Open Conference of

作者： Saloua Lagnaoui Khaoula Boumais Saad El Fallah Zakariae En-Naimani Khalid Haddouch Dalius Matuzevičius Laboratory Engineering Systems and Applications ENSA Sidi Mohamed Ben Abdellah University Fez Morocco Laboratory AI Data Science and Emerging Systems Sidi Mohammed ben Abdallah University ENSA Fez Morocco Systems and Sustainable Environment Laboratory Faculty of Engineering Sciences Private University of Fez Fez Morocco Laboratory Computer Science AI and Cyber Security ENSET University of Hassan II Casablanca Mohammedia Morocco Department of Electronic Systems Faculty of Electronics Vilnius Gediminas Technical University Vilnius Lithuania

ISBN: (数字)9798350352412

ISBN: (纸本)9798350352429

Convolutional Neural Networks are instrumental in artificial intelligence, especially in image processing, where their ability to autonomously learn hierarchical features has led to significant breakthroughs. However, the success of these models is intricately tied to the judicious choice of hyperparameters, which include the configuration of convolutional layers, activation functions, and kernel initialization methods. This research explores kernel initialization methods in Convolutional Neural Network models, seven diverse initialization methods (Glorot Uniform, Ones initialization, Zero initialization, Constant initialization, Random initialization, HeNormal initialization, and Orthogonal initialization) are comprehensively compared. The primary objective is to showcase the sensitivity of Convolutional Neural Networks to these various initialization techniques. The study not only aims to reveal the nuanced impact of kernel initialization but also introduces an adaptive method to enhance model performance. By delving into the intricacies of initialization methods, this research contributes to the improvement of Convolutional Neural Networks effectiveness, especially in critical applications like Plant Disease classification.

关键词： Training Plant diseases Adaptation models Sensitivity Neural networks Convolutional neural networks Kernel

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：