检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,232 篇 会议
54 篇 期刊文献
3 册 图书
1 篇 学位论文

馆藏范围

2,290 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,649 篇 工学
- 1,192 篇 计算机科学与技术...
- 701 篇 电气工程
- 507 篇 软件工程
- 478 篇 信息与通信工程
- 191 篇 控制科学与工程
- 101 篇 电子科学与技术（可...
- 44 篇 航空宇航科学与技...
- 43 篇 机械工程
- 31 篇 生物工程
- 30 篇 石油与天然气工程
- 30 篇 交通运输工程
- 25 篇 仪器科学与技术
- 25 篇 动力工程及工程热...
- 21 篇 建筑学
- 20 篇 生物医学工程（可授...
- 19 篇 土木工程
- 18 篇 光学工程
- 17 篇 材料科学与工程（可...
265 篇 理学
- 133 篇 数学
- 78 篇 物理学
- 43 篇 系统科学
- 40 篇 生物学
- 17 篇 统计学（可授理学、...
188 篇 管理学
- 153 篇 管理科学与工程(可...
- 57 篇 工商管理
- 36 篇 图书情报与档案管...
76 篇 医学
- 51 篇 基础医学(可授医学...
- 33 篇 临床医学
27 篇 经济学
- 27 篇 应用经济学
25 篇 教育学
- 24 篇 教育学
15 篇 法学
8 篇 军事学
3 篇 农学
2 篇 文学
1 篇 艺术学

主题

171 篇 computer archite...
165 篇 programming
91 篇 hardware
86 篇 network architec...
80 篇 linear programmi...
71 篇 neural networks
68 篇 protocols
64 篇 network topology
62 篇 optimization
57 篇 computational mo...
52 篇 deep learning
52 篇 computer network...
49 篇 routing
49 篇 cloud computing
45 篇 application soft...
45 篇 network-on-chip
42 篇 dynamic programm...
41 篇 switches
40 篇 throughput
39 篇 parallel program...

机构

7 篇 univ calif berke...
6 篇 xidian univ stat...
5 篇 natl res univ hi...
5 篇 deakin univ sch ...
5 篇 swiss fed inst t...
5 篇 mit cambridge ma...
5 篇 tsinghua univ pe...
5 篇 southeast univ n...
5 篇 dalian univ tech...
5 篇 russian acad sci...
4 篇 pg demidov yaros...
4 篇 georgia inst tec...
4 篇 univ chinese aca...
4 篇 shanghai jiao to...
4 篇 peking universit...
4 篇 pacific northwes...
4 篇 univ calif san d...
3 篇 columbia univers...
3 篇 univ estadual ca...
3 篇 nanjing univ aer...

作者

10 篇 carle georg
6 篇 magedanz thomas
6 篇 emmerich paul
5 篇 zhao bo
5 篇 benini luca
5 篇 georg carle
4 篇 zhang tao
4 篇 wang lei
4 篇 garcia jordi
4 篇 dongarra jack
4 篇 hoefler torsten
4 篇 li tao
4 篇 turdakov denis
4 篇 luca foschini
4 篇 kellerer wolfgan...
4 篇 vetter jeffrey s...
4 篇 liu derong
4 篇 chatha karam s.
4 篇 li ming
4 篇 lee seyong

语言

2,231 篇 英文
47 篇 其他
10 篇 中文
1 篇 西班牙文
1 篇 土耳其文

检索条件"任意字段=IEEE Conference on Open Architectures and Network Programming"

共 2290 条记录，以下是641-650 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition

CLFace: A Scalable and Resource-Efficient Continual Learning...

引用

ieee Workshop on Applications of Computer Vision (WACV)

作者： Md Mahedi Hasan Shoaib Meraj Sami Nasser Nasrabadi West Virginia University Morgantown West Virginia USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

An important aspect of deploying face recognition (FR) algorithms in real-world applications is their ability to learn new face identities from a continuous data stream. However, the online training of existing deep neural network-based FR algorithms, which are pre-trained offline on large-scale stationary datasets, encounter two major challenges: (I) catastrophic forgetting of previously learned identities, and (II) the need to store past data for complete retraining from scratch, leading to significant storage constraints and privacy concerns. In this paper, we introduce CLFace, a continual learning framework designed to preserve and incrementally extend the learned knowledge. CLFace eliminates the classification layer, resulting in a resource-efficient FR model that remains fixed throughout lifelong learning and provides label-free supervision to a student model, making it suitable for open-set face recog-nition during incremental steps. We introduce an objective function that employs feature-level distillation to reduce drift between feature maps of the student and teacher models across multiple stages. Additionally, it incorpo-rates a geometry-preserving distillation scheme to maintain the orientation of the teacher model's feature embedding. Furthermore, a contrastive knowledge distillation is incor-porated to continually enhance the discriminative power of the feature representation by matching similarities between new identities. Experiments on several benchmark FR datasets demonstrate that CLFace outperforms baseline approaches and state-of-the-art methods on unseen identities using both in-domain and out-of-domain datasets.

关键词： Training Continuing education Data privacy Computer vision Face recognition Benchmark testing Linear programming

来源：评论

学校读者我要写书评

暂无评论

Comparison of Convolutional Neural network architectures and their Influence on Patient Classification Tasks Relating to Altered Mental Status

Comparison of Convolutional Neural Network Architectures and...

引用

ieee International conference on Bioinformatics and Biomedicine (ieee BIBM)

作者： Gagnon, Kevin Crawford, Tami L. Obeid, Jihad Univ South Carolina Comp Sci Columbia SC 29208 USA Med Univ South Carolina Biomed Informat Charleston SC 29425 USA

ISBN: (纸本)9781728162157

With the pervasiveness of Electronic Health Records in many hospital systems, the application of machine learning techniques to the field of health informatics has become much more feasible as large amounts of data become more accessible. In our experiment, we evaluated several different convolutional neural network architectures that are typically used in text classification tasks. We then tested those models based on 1,113 histories of present illness. (HPI) notes. This data was run over both sequential and multi-channel architectures, as well as a structure that implemented attention methods meant to focus the model on learning the influential data points within the text. We found that the multi-channel model performed the best with an accuracy of 92%, while the attention and sequential models performed worse with an accuracy of 90% and 89% respectively.

关键词： Machine Learning Deep Learning Bioinformatics Natural Language Processing Medical Informatics Computing

来源：评论

学校读者我要写书评

暂无评论

Securing the EDK II Image Loader

Securing the EDK II Image Loader

引用

Ivannikov Ispras open conference (ISPRAS)

作者： Haeuser, Marvin Cheptsov, Vitaly Tech Univ Kaiserslautern Kaiserslautern Germany Russian Acad Sci Ivannikov Inst Syst Programming Moscow Russia

ISBN: (纸本)9781665412919

The Unified Extensible Firmware Interface (UEFI) is a standardised interface between the firmware and the operating system used in all x86-based platforms over the past ten years, which continues to spread to other architectures such as ARM and RISC-V. The UEFI incorporates a modular design based on images containing a driver or an application in a Common Object File Format (COFF) either as a Portable Executable (PE) or as a Terse Executable (TE). The de-facto standard generic UEFI services implementation, including the image loading functionality, is TianoCore EDK II. Its track of security issues shows numerous design and implementation flaws some of which are yet to be addressed. In this paper we outline both the requirements for a secure UEFI Image Loader and the issues of the existing implementation. As an alternative we propose a formally verified Image Loader supporting both PE and TE images with fine-grained hardening enabling a seamless integration with EDK II and subsequently with the other firmwares.

关键词： UEFI Parsing Security Program verification

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural network Approach to Diabetic Retinopathy Detection and its Automated Classification 7

A Convolutional Neural Network Approach to Diabetic Retinopa...

引用

7th International conference on Advanced Computing and Communication Systems, ICACCS 2021

作者： Seetah, Himshikha Singh, Nidhi Meel, Priyanka Dhudi, Tript Delhi Technological University Department of Information Technology New Delhi India

ISBN: (纸本)9781665405201

Diabetic Retinopathy is the result of the deterioration of blood vessels in the retina. Diabetic patients are more likely to develop this problem after a prolonged suffering and a lack of recommended control over their blood sugar level. It figures among the significant causes leading to blindness globally. It is majorly classified into four categories: firstly, mild non-proliferative, moderate non-proliferative, severe non-proliferative, proliferative diabetic retinopathy. Since, it is a very tedious task to manually diagnose such diseases, we have built a mechanism after studying various existing programs which help in identifying the correct stage of diabetic retinopathy. This paper identifies various methodologies and architectures such as Convolutional Neural network which performs detection using colour fundus photographs of the human retina. The dataset used for training and testing was obtained from the open-source platform, Kaggle. The model proposed and implemented in this paper gave an accuracy of 84 percent and this work specifically targeted improvements in specificity and sensitivity, leading to achieving 98.25 percent and 98 percent for both respectively. This research strengthens the notion that such algorithms play a key role in the field of medical and technology. They help in quick processing and deep investigation of medical problem. © 2021 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection of Asphalt Pavement Cracks with YOLO architectures from Unmanned Aerial Vehicle Images

Detection of Asphalt Pavement Cracks with YOLO Architectures...

引用

ieee Signal Processing and Communications Applications (SIU)

作者： Ebrar Ödübek Muhammed Enes Atik Geomatik Mühendisliği İstanbul Teknik Üniversitesi İstanbul Türkiye

ISBN: (数字)9798350388961

ISBN: (纸本)9798350388978

Monitoring road condition has been a strategic area of research in maintaining an extensive transportation infrastructure network. Although damages on road surfaces initially appear as slight cracks, the depth and danger of these damages may increase over time and changing weather conditions. Cracks on the road surface are one of the main factors affecting the performance of the road. Automatic detection of road cracks is an important task in road maintenance. However, automatic crack detection is a challenging application area due to the inhomogeneity of the density of cracks and the complexity of the background (e.g. low contrast with the surrounding coating and possible shadows of similar intensity). Recently, deep learning-based object detection and segmentation methods have begun to be used effectively in detecting cracks on road surfaces. In this study, a comparative analysis was carried out for the detection of cracks on road surfaces using the current versions of You Only Look Once (YOLO), a popular single-step object detection algorithm. The open source dataset UAPD, consisting of unmanned aerial vehicle (UAV) images, was used in the analysis. In the application carried out to detect different types of cracks with YOLOv5x, 0.639 mean average precision (mAP) and 0.759 sensitivity metrics were obtained. Using the YOLOv5x algorithm, the highest accuracy was achieved compared to other algorithms.

关键词： YOLO Sensitivity Roads Signal processing algorithms Transportation Signal processing Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

Analysis of Deep Neural network architectures and Similarity Metrics for Low-Dose CT Reconstruction 7

Analysis of Deep Neural Network Architectures and Similarity...

引用

7th ieee open conference of Electrical, Electronic and Information Sciences, eStream 2020

作者： Brusokas, Jonas Petkevicius, Linas Vilnius University Institute of Computer Science Vilnius Lithuania

ISBN: (纸本)9781728197791

Computed tomography (CT) is a widely used imaging technique in the medical field. During CT procedures patients are exposed to high amounts of radiation, posing a tangible threat to their health. Developed low-dose procedures lower exposure but produce noise and artifacts in images. To improve diagnostic accuracy, deep learning techniques are proposed to remove noises and artifacts from low-dose images. In this paper, the performance of several neural network architectures and similarity metrics as loss functions for low-dose CT image reconstruction are analyzed. Experimental results showed that selection of loss function can have significant impact on model performance, with the GSSIM metric outperforming other contemporary metrics SSIM, MSSSIM and MSE. Experiments were conducted using open-access and local cancer research institution data. © 2020 ieee.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Sustainability of 5G Green network toward D2D Communication with RF- Energy Techniques

Sustainability of 5G Green Network toward D2D Communication ...

引用

2021 International conference on Intelligent Technologies, CONIT 2021

作者： Pradhan, Devasis Sahu, Prasanna Kumar Dash, A. Tun, Hla Myo Acharya Institute of Technology Department of Electronics and Communication Engineering Dr. Sarvepalli Radha Krishnan Road Bengaluru India NIT Rourkela Department of Electrical Engineering Odisha India Department of Electronics and Telecommunication Engineering India Yangon Technological University Faculty of Electrical and Computer Engineering Department of Electronic Engineering Myanmar

ISBN: (纸本)9781728185835

As the world pushes toward the utilization of greener innovation and limits energy squander, energy productivity in the remote organization has gotten more basic than any other time in recent memory. The cutting edge network, for example, 5G, are being intended to improve energy productivity and accordingly establish a basic part of the exploration and network planning. The 5G Green era required to convey a wide scope of administrations that incorporates upgraded versatile broadband, gigantic machine-type correspondence and ultra-dependability, and low inertness. Presently various difficulties and open doors for the plan of modern client affiliation instruments. Thus, considerable examination endeavors are committed to the issues of client relationship in HetNets, massive MIMO, mmWave, and energy harvesting. The paper further discussed the new security highlights including various innovations applied to 5G Green Communication, such as heterogeneous networks, gadget to-gadget interchanges or D2D Communication, enormous different info numerous yield, programming characterized networks, and the Internet of Things(IoT). © 2021 ieee.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Virtualized network Graph Design and Embedding Model 9

Virtualized Network Graph Design and Embedding Model

引用

ieee 9th International conference on Cloud networking (CloudNet)

作者： Sato, Takehiro Kurimoto, Takashi Urushidani, Shigeo Oki, Eiji Kyoto Univ Kyoto Japan Natl Inst Informat Kyoto Japan

ISBN: (纸本)9781728194868

This paper proposes an optimization model for virtualized network graph design and embedding (VNDE), which is applied for a scenario in which a single entity fulfills both roles of a service provider and an infrastructure provider. The VNDE model determines the number of virtual routers (VRs) and a virtual network (VN) graph for each VN request in conjunction with the VN embedding. Numerical results show that the proposed model designs VN graphs and embeds them into the substrate infrastructure according to the volume of traffic demands and access path cost.

关键词： network virtualization optimization model integer linear programming

来源：评论

学校读者我要写书评

暂无评论

TOSS-2020: A Commodity Software Stack for HPC

TOSS-2020: A Commodity Software Stack for HPC

引用

International conference on High Performance Computing, networking, Storage and Analysis (SC)

作者： Leon, Edgar A. D'Hooge, Trent Hanford, Nathan Karlin, Ian Pankajakshan, Ramesh Foraker, Jim Chambreau, Chris Leininger, Matthew L. Lawrence Livermore Natl Lab Livermore Comp Livermore CA 94550 USA

ISBN: (纸本)9781728199986

The simulation environment of any HPC platform is key to the performance, portability, and productivity of scientific applications. This environment has traditionally been provided by platform vendors, presenting challenges for HPC centers and users including platform-specific software that tend to stagnate over the lifetime of the system. In this paper, we present the Tri-Laboratory Operating System Stack (TOSS), a production simulation environment based on Linux and open source software, with proprietary software components integrated as needed. TOSS, focused on mid-to-large scale commodity HPC systems, provides a common simulation environment across system architectures, reduces the learning curve on new systems, and benefits from a lineage of past experience and bug fixes. To further the scope and applicability of TOSS, we demonstrate its feasibility and effectiveness on a leadership-class supercomputer architecture. Our evaluation, relative to the vendor stack, includes an analysis of resource manager complexity, system noise, networking, and application performance.

关键词： Scientific computing Accelerator architectures Parallel architectures Multicore processing Multiprocessor interconnection networks Parallel machines Supercomputers Processor scheduling Cluster computing High performance computing Software performance Software reusability System software Operating systems Utility programs programming environments Runtime Runtime environment Software libraries

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing in Real-time Alarm Information Push of DingTalk Platform

Cloud Computing in Real-time Alarm Information Push of DingT...

引用

Telecommunications, Optics and Computer Science (TOCS), ieee conference on

作者： Helin Zhang Meiling Jiang Dongying Gao Dewei Lin Ning Ding Zhiwei Zheng Haosong Sun State Grid Fujian Information & Telecommunication Company Fuzhou China

ISBN: (纸本)9781665470544

In recent years, real-time alarm information push technology has achieved rapid development. With the continuous maturity of the browser platform, the application of real-time alarm information will continue to advance. The research purpose of this paper is to study the application of cloud computing in real-time alarm information push of Dingding platform. First, it introduces the definition of cloud computing and the current research mainstream cloud computing platforms, then focuses on the distributed architecture of the Hadoop open source cloud computing platform, and introduces two key elements of the Hadoop architecture, the distributed MapReduce computing model and distributed HDFS files system. Finally, the specific design idea of the improved PrefixSpan algorithm based on the distributed programming model of the cloud computing platform MapReduce and the analysis of the performance results of the improved algorithm are introduced in detail. The experimental results show that the SK2 algorithm has the highest accuracy rate, because the alarm Bayesian network topology obtained by the algorithm is closer to the logical topology of the network.

关键词： Cloud computing network topology Databases Computational modeling Computer architecture Big Data Real-time systems

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共229页 << < 61 62 63 64 65 66 67 68 69 70 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：