检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Yunong Zhang Zhiwen Yuan School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Research Institute of Sun Yat-sen University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper presents three relatively effective numerical algorithms,i.e.,94 LVI algorithms of OIpU(one-iteration-perupdate) type,to handle time-dependent QP(quadratic programming) problems subject to two constraints respectively(i.e.,equality and inequality constraints,equality and bound constraints,or inequality and bound constraints).Specifically,two "bridges" play essential parts of the methods(i.e.,the first "bridge" makes a QP problem convert to an LVI [linear variational inequality],and the second "bridge" makes the LVI convert to a PLPE [piecewise-linear projection equation]).On the basis of the standard94 LVI algorithm,the methods only update once through the solution of the previous sampling time ***,we conduct a number of experiments to substantiate the three algorithms respectively,which use exponential functions,log functions,and trigonometric functions in corresponding coefficients of the experimental examples.

关键词： Quadratic programming Time-dependent Numerical algorithms Linear variational inequalities(LVI)

来源：评论

学校读者我要写书评

暂无评论

First-principles investigation of microscopic mechanisms underlying hole mobilities in diamond, silicon, and germanium

引用

Physical Review B 2024年第15期110卷 155203页

作者： Qiao-Lin Yang Fan-Chen Meng Wu Li Zhi Wang Hui-Xiong Deng Su-Huai Wei Fan-long Ning Jun-Wei Luo School of Physics and Zhejiang Key Laboratory of Micro-Nano Quantum Chips and Quantum Control State Key Laboratory of Superlattices and Microstructures Research Computing and Data Eastern Institute for Advanced Study Center of Materials Science and Optoelectronics Engineering State Key Laboratory of Silicon and Advanced Semiconductor Materials

Silicon (Si) dominates the semiconductor industry but currently suffers from significant hole mobility degradation in advanced transistors due to its abnormally low hole mobility (505cm2/Vs), compared to its group IV neighbors, diamond and germanium (Ge) (both ∼2000cm2/Vs). While Ge's high mobility is understandable by its lighter effective hole mass due to its narrower direct bandgap at Γ point, diamond's superior hole mobility remains difficult to understand since its bandgap is ultrawide. Conventional wisdom attributes diamond's high mobility to reduced phonon scattering due to high acoustic phonon group velocity and optical phonon frequency, overcoming its heaviest effective mass. However, our study reveals that this mechanism alone is insufficient to explain the observed mobility. We demonstrate that the diamond's abnormally light effective hole mass is a primary factor contributing to its high mobility; otherwise, its hole mobility would be approximately nine times lower than Si's. The unexpectedly light mass in diamond stems from larger transition matrix elements, resulting from substantial electronic wave-function overlap between valence and conduction bands, remarkably overcoming the effect of diamond's large bandgap. Furthermore, our investigation uncovers a unique feature in diamond's valence band structure: an inherent strain-enhanced mobility characteristic, where the top valence band manifests as a light-hole (lh) state along certain crystallographic directions (e.g., [100]), instead of the typical heavy-hole (hh) state. Contrary to prevailing assumptions, we observe a strong coupling between holes and transverse acoustic (TA) phonons, and even TA scattering dominates over longitudinal acoustic (LA) scattering in both diamond and Si, challenging the long-held belief that TA scattering is negligible. Our calculations yield a dilation deformation potential of 3.45 eV for diamond, significantly diverging from previously reported values, e.g., 7 or −35 eV.

关键词： Electrical conductivity Electron-phonon coupling Semiconductors Density functional calculations Wannier function methods

来源：评论

学校读者我要写书评

暂无评论

NFDI4Health Workflow and Service for Synthetic Data Generation, Assessment and Risk Management

NFDI4Health Workflow and Service for Synthetic Data Generati...

引用

69th Annual Meeting of the German Association of Medical Informatics, Biometry and Epidemiology, GMDS 2024

作者： Moazemi, Sobhan Adams, Tim Ng, Hwei Geok Kühnel, Lisa Schneider, Julian Näher, Anatol-Fiete Fluck, Juliane Fröhlich, Holger Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing SCAI Sankt Augustin Germany Knowledge Management ZB MED - Information Centre for Life Sciences Cologne Germany Faculty of Technology Bielefeld University Bielefeld Germany Digital Global Public Health Hasso Plattner Institute for Digital Engineering University of Potsdam Potsdam Germany Institute of Medical Informatics Charité-Universitätsmedizin Germany Method Development Research Infrastructure and Information Technology Robert Koch Institute Berlin Germany The Agricultural Faculty University of Bonn Bonn Germany Institute for Geodesy and Geoinformation University of Bonn Bonn Germany University of Bonn Bonn Germany

ISBN: (纸本)9781643685366

Individual health data is crucial for scientific advancements, particularly in developing Artificial Intelligence (AI);however, sharing real patient information is often restricted due to privacy concerns. A promising solution to this challenge is synthetic data generation. This technique creates entirely new datasets that mimic the statistical properties of real data, while preserving confidential patient information. In this paper, we present the workflow and different services developed in the context of Germany's National Data Infrastructure project NFDI4Health. First, two state-of-the-art AI tools (namely, VAMBN and MultiNODEs) for generating synthetic health data are outlined. Further, we introduce SYNDAT (a public web-based tool) which allows users to visualize and assess the quality and risk of synthetic data provided by desired generative models. Additionally, the utility of the proposed methods and the web-based tool is showcased using data from Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Center for Cancer Registry Data of the Robert Koch institute (RKI). © 2024 The Authors.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Federated Focal Modulated UNet for Cardiovascular Image Segmentation

Federated Focal Modulated UNet for Cardiovascular Image Segm...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Asjad, Mohammad Qayyum, Abdul Mazher, Moona Naseem, Usman Khan, Tariq Niederer, Steven Razzak, Imran Indian Institute of Technology Kharagpur India Imperial College London National Heart and Lung Institute Faculty of Medicine London United Kingdom The Alan Turing Institute Turing Research and Innovation Cluster: Digital Twins London United Kingdom University College London Department of Computer Science London United Kingdom Macquarie University School of Computing Australia University of New South Wales School of Computer Science and Engineering Australia

ISBN: (纸本)9798350362480

Federated learning facilitates collaborative training of machine learning models on data distributed across multiple locations, effectively addressing the privacy concerns by eliminating the need for data centralization - a critical consideration in medical image analysis. In healthcare applications like cardiovascular segmentation, datasets from individual sites often feature annotations for specific heart regions, leading to partial overlaps. To address this challenge, we present a two-step partial annotation framework for federated learning, featuring a hybrid 3D multi-encoding UNet enhanced with focal modulation layers in the second stage. This architecture enables specialized subnetworks to act as experts, extracting features tailored to specific regions of interest based on each client's data. To further improve feature extraction and differentiation, we incorporate focal modulation blocks and apply regularization by introducing an auxiliary generic decoder during training. Comprehensive experiments on diverse cardiac MRI datasets demonstrate that our approach significantly outperforms centralized learning models. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

The Prospect of Enhancing Large-Scale Heterogeneous Federated Learning with Foundation Models

The Prospect of Enhancing Large-Scale Heterogeneous Federate...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yulan Gao Zhaoxiang Hou Chengyi Yang Zengxiang Li Han Yu Xiaoxiao Li College of Computing and Data Science Nanyang Technological University Singapore Digital Research Institute ENN Group China Department of Electrical and Computer Engineering The University of British Columbia Canada

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Federated learning (FL) addresses data privacy concerns by enabling collaborative training of AI models across distributed data owners. Wide adoption of FL faces the fundamental challenges of data heterogeneity and the large scale of data owners involved. In this paper, we investigate the prospect of Foundation Model (e.g., transformers)-based FL for achieving generalization and personalization in this setting. Different from existing research efforts which mostly focus on studying Transformer-based FL on small scales, we conduct extensive comparative experiments involving FL with Transformers, ResNet, and personalized ResNet-based FL approaches under various large-scale scenarios. These experiments consider varying numbers of data owners to demonstrate Transformers’ advantages over deep neural networks in large-scale heterogeneous FL tasks. In addition, we analyze the superior performance of Transformers by comparing the Centered Kernel Alignment (CKA) representation similarity across different layers and FL models to gain insight into the reasons behind their promising capabilities.

关键词： Training Analytical models Data privacy Accuracy Federated learning Distributed databases Transformers

来源：评论

学校读者我要写书评

暂无评论

CM-HTNet: CNN-Mamba-based Framework for Predicting Hemorrhagic Transformation Risk of AIS Patients using Sequence Relationship Modeling and Multi-Modal Cross Attention

CM-HTNet: CNN-Mamba-based Framework for Predicting Hemorrhag...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Huang, Yuxiang Ren, Huanhuan Li, Yongmei Jiang, Jingfeng Xu, Haodong Feng, Jinwang Cui, Shaoguo Chongqing Normal University College of Computer and Information Science China Chongqing University Cancer Hospital and Chongqing Cancer Institute and Chongqing Cancer Hospital Department of Radiology China First Affiliated Hospital of Chongqing Medical University Department of Radiology China Michigan Technological University Center for Biocomputing and Digital Health Institute of Computing and Cybernetics and Health Research Institute United States Michigan Technological University Department of Biomedical Engineering United States

ISBN: (纸本)9798350386226

Hemorrhagic transformation (HT) is a severe complication of acute ischemic stroke (AIS) that can lead to disability or death. Accurate and timely risk assessment of HT is essential for clinicians to design effective treatment strategies. Previous studies in HT prediction have largely relied on machine learning and radiomics, which demand extensive manual data preprocessing by physicians. While some HT prediction models based on convolutional neural network (CNN) have been developed, they are limited in their ability to capture the sequential relationships between image slices and often lack the focus on crucial information. This study collected non-contrast computed tomography (NCCT) images and clinical data from 512 AIS patients across six hospitals to create a multi-center dataset. Based on the dataset, we propose CM-HTNet, a novel deep learning framework designed to predict HT risk in AIS patients following intravenous thrombolysis (IVT). CM-HTNet mimics the clinical process of reviewing NCCT images by focusing on key slices and integrating information from adjacent slices. It leverages CNNs to extract features from each NCCT slice and utilizes the Selective State-Space Model (SSM) within the Mamba framework to model sequential relationships between slices while prioritizing features relevant to HT prediction. Additionally, CM-HTNet incorporates the Neighborhood Rough Set (KRS) algorithm for clinical feature selection and cross-attention mechanisms to integrate clinical and imaging data for multimodal HT risk prediction. In testing on an external dataset from independent centers, CM-HTNet achieved a prediction accuracy of 88.85% and an AUC of 95.17%, showcasing its strong performance and generalization capabilities. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An empirical IoT and cloud-based customizable healthcare surveillance system

引用

International Journal of Information Technology (Singapore) 2024年第8期16卷 5317-5323页

作者： Meti, Subhash Razauddin, S. Nallakumar, R. Mansingh, P. M. Benson Sameen, Aws Zuhair Pandey, Sakshi Bhatt, Sanjeev Kumar Jayabalan, Bhuvana Department of Electronics and Communication Engineering SKSVMACET Lakshmeshwar Karnataka Gadag India College of Computer Science and Engineering University of Hail Hail Saudi Arabia Department of Artificial Intelligence and Data Science Karpagam Institute of Technology Coimbatore India Department of Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Andhra Pradesh Guntur India College of Medical Techniques Al-Farahidi University Baghdad Iraq Centre of Interdisciplinary Research in Business and Technology Chitkara Institute of Engineering and Technology Chitkara University Punjab Rajpura India Software Architect and Research Scholar Digital Innovation College PDM University Bahadurgarh India Department of Computer Science and Information Technology JAIN (Deemed-to-Be University) Karnataka Bengaluru India

In certain emergencies, patients must be continuously monitored and cared for. However, visiting the hospital to do such activities is difficult because of time constraints. To modernize the healthcare sector, the study in question presents an empirical Internet of Things and cloud-based, customizable healthcare monitoring system. Initially, a cloud-based algorithm called particle swarm intelligence (PGI) is used in the proposed healthcare monitoring system to group recorded data, hence increasing the prediction rate. Subsequently, features are selected and extracted, and back propagation neural networks (BPNN) are employed to classify healthcare for humans. In the end, the effectiveness of the suggested system is evaluated using a healthcare dataset and contrasted with current deep learning/machine learning classifiers. The suggested surveillance system performs better than the methods employed in the previous research, according to the findings. © Bharati Vidyapeeth's institute of Computer Applications and Management 2024.

关键词： BPNN Cloud computing Healthcare surveillance IoT Particle swarm intelligence (PSI)

来源：评论

学校读者我要写书评

暂无评论

Single track analysis of additive manufactured SS 316L based composites using powder bed fusion 4

Single track analysis of additive manufactured SS 316L based...

引用

4th Innovative Product Design and Intelligent Manufacturing Systems, IPDIMS 2022

作者： Benarji, K. Jinoop, A.N. Ravikumar, Y. Paul, C.P. Department of Mechanical Engineering Centurion University Odisha Paralakhemundi761211 India Laser Technology Division Raja Ramanna Centre for Advanced Technology Madhya Pradesh Indore452013 India School of Computing Engineering & Digital Technologies Teesside University MiddlesbroughTS1 3BX United Kingdom Department of Mechanical Engineering National Institute of Technology Warangal Telangana Warangal506004 India Homi Bhabha National Institute Anushaktinagar Maharashtra Mumbai400094 India

The inadequate wear resistance and hardness of SS 316L make it unsuitable for use in harsh mechanical conditions. The present study reports the deployment of powder bed fusion (PBF) to create B4C particle-reinforced SS 316L composites to improve the mechanical properties of SS 316L. The study focuses on the influence of PBF process parameters on the track width (TW), track depth (TD), surface morphology, hardness, and surface roughness of a single track. TW and TD both increase with laser power (LP). The maximum hardness of 328 HV and minimum surface roughness of 0.07 lm are seen at LP of 300 W, and laser travel speed of 0.06 m/min. The absence of B4C particles is noticed at high laser powers due to the low density of reinforcement particles. Copyright © 2023 Elsevier Ltd. All rights reserved.

关键词： Rockwell hardness

来源：评论

学校读者我要写书评

暂无评论

Global Reliable Diagnosis of Networks Based on Self-Comparative Diagnosis Model and G-Good-Neighbor Property

SSRN

引用

SSRN 2024年

作者： Wang, Mujiangshan Xu, Shuhao Jiang, Jincheng Xiang, Dong Hsieh, Sun-Yuan Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Software Tsinghua University Beijing100084 China Department of Computer Science and Information Engineering National Cheng Kung University Tainan701 Taiwan Guangdong Academy of Agricultural Sciences China

In the research field of system-level diagnosis, people used to focus on studying different diagnosabilities with restrictions. By studying this, reliability measured by these diagnosabilities of various of networks is obtained. However, for the decentralized parallel computing systems, there are always upper bonds for diagnosabilities, which means there exists an undiagnosable subnetwork cut off by a faulty vertex cut if the subnetwork is large enough. In this paper, we set up a 2-stage plan for the global reliable diagnosis of networks combining Self-Comparative diagnosis (SC) model and the g-good-neighbor property, which means every vertex in the networks is diagnosed with high accuracy. Six algorithms are proposed for the realization of the plan and diagnosis model for g≥2. In the end, we code a simulator for the plan and test how well it works and the codes are provided via Github link for readers' check. © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quaternary ammonium-functionalized polysilsesquioxanes for antifogging coating

RSC Applied Polymers

引用

RSC Applied Polymers 2024年第1期3卷 92-96页

作者： Hamada, Takashi Sugimoto, Tetsuya Tanaka, Arata Maeda, Tetsuya Katsura, Daiji Koga, Hiroyuki Ohshita, Joji Collaborative Research Laboratory Graduate School of Advanced Science and Engineering Hiroshima University 1-4-1 Kagamiyama Higashi-Hiroshima Hiroshima 739-8527 Japan Quantum Materials and Applications Research Center Takasaki Institute for Advanced Quantum Science National Institutes for Quantum Science and Technology (QST) 1233 Watanuki-machi Takasaki Gunma 370-1292 Japan Technical Research Center Mazda Motor Corporation Aki-gun Hiroshima 730-8670 Japan Smart Innovation Program Graduate School of Advanced Science and Engineering Hiroshima University 1-4-1 Kagamiyama Higashi-Hiroshima Hiroshima 739-8527 Japan Division of Materials Model-Based Research Digital Monozukuri (Manufacturing) Education and Research Center Hiroshima University 3-10-32 Kagamiyama Higashi-Hiroshima Hiroshima 739-0046 Japan

Aiming to develop antifogging materials with enhanced antifogging properties and scratch resistance, polysilsesquioxane films containing quaternary ammonium groups were prepared via a sol-gel reaction and quaternization. Owing to their high water uptake, scratch hardness, and transparency, the prepared quaternary ammonium-functionalized polysilsesquioxane films are promising for application in antifogging coatings. © 2025 RSC.

关键词：

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：