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

36,825 篇 会议
803 篇 期刊文献
554 册 图书

馆藏范围

38,181 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

28,173 篇 工学
- 16,412 篇 计算机科学与技术...
- 13,243 篇 软件工程
- 4,886 篇 机械工程
- 4,503 篇 控制科学与工程
- 4,428 篇 信息与通信工程
- 3,414 篇 电气工程
- 2,909 篇 电子科学与技术（可...
- 2,231 篇 材料科学与工程（可...
- 2,173 篇 化学工程与技术
- 2,009 篇 生物工程
- 1,885 篇 仪器科学与技术
- 1,850 篇 生物医学工程（可授...
- 1,813 篇 光学工程
- 1,753 篇 动力工程及工程热...
- 1,509 篇 冶金工程
- 1,431 篇 力学（可授工学、理...
- 1,307 篇 土木工程
- 1,068 篇 建筑学
13,559 篇 理学
- 7,038 篇 数学
- 4,266 篇 物理学
- 2,229 篇 生物学
- 1,883 篇 化学
- 1,844 篇 统计学（可授理学、...
- 1,368 篇 系统科学
7,571 篇 管理学
- 5,353 篇 管理科学与工程(可...
- 2,466 篇 图书情报与档案管...
- 2,182 篇 工商管理
1,403 篇 医学
- 1,174 篇 临床医学
- 1,068 篇 基础医学(可授医学...
1,277 篇 教育学
- 1,211 篇 教育学
900 篇 经济学
886 篇 法学
690 篇 农学
371 篇 文学
170 篇 军事学
149 篇 艺术学
11 篇 哲学
6 篇 历史学

主题

642 篇 computer science
526 篇 computational mo...
391 篇 mechatronics
356 篇 deep learning
341 篇 computer archite...
296 篇 scientific compu...
283 篇 support vector m...
267 篇 internet of thin...
256 篇 software enginee...
244 篇 data mining
235 篇 artificial intel...
224 篇 feature extracti...
222 篇 image segmentati...
212 篇 machine learning
212 篇 accuracy
198 篇 training
194 篇 big data
186 篇 application soft...
186 篇 computer vision
178 篇 neural networks

机构

54 篇 school of comput...
52 篇 school of automa...
47 篇 kunming universi...
46 篇 school of comput...
44 篇 college of compu...
44 篇 computer technol...
41 篇 department of co...
41 篇 school of mechat...
37 篇 college of mecha...
36 篇 université de st...
34 篇 università di ca...
34 篇 infn sezione di ...
34 篇 north-west unive...
34 篇 in2p3 lpc campus...
34 篇 institut univers...
34 篇 national centre ...
34 篇 tno technical sc...
33 篇 infn sezione di ...
33 篇 maharishi school...
31 篇 college of compu...

作者

48 篇 liu yang
40 篇 wang jian
39 篇 wang lei
36 篇 li li
35 篇 ferrara g.
35 篇 ardid m.
35 篇 kalekin o.
35 篇 díaz a.f.
34 篇 chen a.
34 篇 benoit d.m.
34 篇 calvo d.
34 篇 gagliardini s.
34 篇 eddymaoui a.
34 篇 gal t.
34 篇 bozza c.
33 篇 zhang lei
33 篇 khatun a.
33 篇 huang f.
33 篇 boumaaza j.
33 篇 coleiro a.

语言

34,596 篇 英文
2,987 篇 其他
742 篇 中文
5 篇 西班牙文
3 篇 俄文
1 篇 捷克文
1 篇 日文
1 篇 葡萄牙文
1 篇 土耳其文

检索条件"任意字段=Scientific Conference on Mechatronics Engineering and Computer Science"

共 38182 条记录，以下是941-950 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：

Object Detection Algorithms with Deep Learning: An Overview 3

Object Detection Algorithms with Deep Learning: An Overview

引用

3rd International conference on Electronic Information engineering and computer science, EIECS 2023

作者： Tang, Wei Chen, Jinlong Ning, Yi Xu, Kejian Guilin University of Electronic Technology School of Computer Science and Information Security Guilin China Guilin University of Electronic Technology School of Continuing Education Guilin China

ISBN: (纸本)9798350316674

Deep learning is a key branch of machine learning that leads the frontier of scientific research and has a significant impact on the field of computer vision. With the development of deep learning, object detection, as a research hotspot in computer vision, has attracted a great number of researchers to conduct in-depth research. This paper introduces single-stage, two-stage and Transformer-based object detection algorithms and its backbone network structures, and provides a detailed comparison of the advantages and shortcomings of these algorithms. Finally, the practical applications of these algorithms in various fields and their performance evaluation on critical datasets are presented. © 2023 IEEE.

关键词： Deep Learning Object Detection Performance Evaluation Transformer

来源：评论

学校读者我要写书评

暂无评论

An Embedded Cellular Automata Algorithm for Infrared Object Detection 33

An Embedded Cellular Automata Algorithm for Infrared Object ...

引用

33rd International scientific conference Electronics, ET 2024

作者： Rizanov, Stefan Yakimov, Peter Nikolov, Dimitar Boydens, Jeroen Technical University of Sofia Faculty of Electronic Engineering and Technologies 8 Kliment Ohridski blvd Sofia1000 Bulgaria KU Leuven Department of Computer Science Spoorwegstraat 12 Bruges8200 Belgium

ISBN: (纸本)9798350376449

This work proposes and presents a cellular automata algorithm for infrared object detection and tracking. The algorithm's application is aimed towards computationally limited edge computing sensory modules. Performed is a statistical evaluation of the algorithm's noise resilience through a 3D histogram method. Proposed is a methodology for the optimal choice of the algorithm's fine-tuning parameter values. The performance influence of applying low-pass Kernel filtering was evaluated and developed was a majority voting-based concurrent object mask-generating algorithm. © 2024 IEEE.

关键词： Cellular automata

来源：评论

学校读者我要写书评

暂无评论

Application of machine learning in automatic fault detection for passive optical network 4

Application of machine learning in automatic fault detection...

引用

4th International conference on Machine Learning and computer Application, ICMLCA 2023

作者： Song, Miao Zhang, Peng College of Computer Science IoT of Chongqing Institute of Engineering Chongqing400056 China China Broadnet Chongqing Corporation Chongqing401147 China

ISBN: (数字)9781510680265

ISBN: (纸本)9781510680258

The transformation of all-optical networks is an important task for communication operators to meet the needs of the new diversified comprehensive information services. The service experience of users was affected by quality of the network directly, network operation and maintenance is an important task of operation. This paper focus on the application of machine learning technology in network operation and maintenance quality analysis;automatically determine fault points by training historical network performance indicators and status data. The method proposed can predict the location of faults, improve the quality and efficiency of PON maintenance and reduce daily maintenance workload. Through practical, the solution proposed has demonstrated feasibility and can provide reference for the construction of intelligent operation and maintenance platforms for network operators. © 2024 SPIE.

关键词： Passive optical networks

来源：评论

学校读者我要写书评

暂无评论

A method for correcting periodic motion artifacts in optical coherence tomography for enhanced vascular imaging

A method for correcting periodic motion artifacts in optical...

引用

2024 International conference on Precision Instruments and Optical engineering, PIOE 2024

作者： Xia, Yule Liu, Zhoubohan School of Mechanical and Electrical Engineering Hunan Bio-Mechatronics Vocational and Technical College Changsha410127 China SEGi University Kuala Lumpur47810 Malaysia

ISBN: (纸本)9781510686120

Decorrelation-based optical coherence tomography angiography (OCTA) is a widely utilized technique that leverages OCT intensity data for imaging. Nevertheless, the quality of these images is often compromised by the cardiac and respiratory motions in animals. These cyclical bulk motions, particularly in the C-Scan (slow scan) direction, obstruct motion correction by altering the scan position and the OCT structure. While various correction methods have been proposed, they frequently result in the loss of vascular information under substantial bulk motion conditions. In this study, we present a novel correction method employing a stitch scan protocol in the C-Scan direction. By setting a threshold for the maximum value of normalized cross-correlation among repeated B-Scan intensity signals, we effectively exclude false OCT B-scans. In vivo imaging experiments on mice demonstrate that our bulk method preserves the complete vascular information and significantly improves image quality. © 2024 SPIE.

关键词： Optical coherence tomography Tunable filters Image quality Animals Signal filtering Angiography In vivo imaging Vascular imaging Electronic filtering Signal intensity

来源：评论

学校读者我要写书评

暂无评论

A Function Fitting System Based on Genetic Algorithm 1

引用

18th International conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Sun, Qiuhong Wang, Jiaqi Zhou, Xiaokang School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang050018 China The Faculty of Data Science Shiga University Hikone522-8522 Japan Department of Computer Science North China Electric Power University Baoding071003 China The RIKEN Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan

ISBN: (数字)9789819998937

ISBN: (纸本)9789819998920

With the development of science and technology, function fitting has penetrated into various fields of scientific research, scientific and technological innovation. For the function of fitting analysis of a given function image, there is no public software on the market that uses the idea of genetic algorithm to solve the problem of function fitting. In order to make up for the insufficiency of the existing software and seize the opportunity of function fitting in various industries, a function fitting system based on genetic algorithm was proposed. It is a low-threshold software with a wide range of applications. When designing the function of fitting and analyzing a given function image, the genetic algorithm is used. With the application of ray detection in Unity, the closest expression of function fitting is obtained. At the same time, the line graph of fitness reduction during genetic algorithm iteration is given. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Study on Fast Stability of New Power System Based on the Method of Gradient Dynamic Deviation and PMU Data 3

Study on Fast Stability of New Power System Based on the Met...

引用

3rd International conference on Electrical engineering and mechatronics Technology, ICEEMT 2023

作者： Hu, Jingxuan Yu, Miao Zhang, Shouzhi Sun, Jianqun Wei, Jingjing Wu, Yixiao Beijing University of Civil Engineering and Architecture School of Mechanical-Electronic and Vehicle Engineering School of Mechatronics and Vehicle Engineering Beijing China

ISBN: (纸本)9798350303698

Driven by dual promotions of energy transformation and scientific technology progress, the high proportion of renewable energy and power electronic equipment (Double-high) are becoming important trends and key features of the development of power system. The dynamic behavior of the power system has undergone major changes. The analysis method of the traditional small signal stability is difficult to use, which brings the great inconvenience to the subsequent calculation and analysis. Moreover, there are still problems to be solved for the rapid change of operating conditions, which puts forward higher requirements for the small interference stability analysis. In this paper, a Lyapunov direct analysis method of gradient dynamic deviation based on PMU data is proposed to analyze the small signal stability of the new power system. Firstly, a PMU data matrix is used to reduce the dimension to obtain the low dimension matrix, which is substituted into the power system matrix model with DFIG. Then, a diagonal matrix is obtained by solving the Lyapunov equation, and the positive definiteness of the matrix is determined to judge the system stability;Secondly, the dynamic deviation value of the corresponding state variable can be calculated by solving the diagonal matrix, and the extreme value of the curve can be calculated by using the gradient descent method for the corresponding state variable curve, and the time weighted dynamic deviation of the whole oscillation process can be calculated by time weighting, which provides guidance for the configuration position of the damping stability controller (PSS) in the system. Finally, the method can improve the small interference stability of the system and the effectiveness of the fast stability analysis of the new power system is verified by the IEEE 10-machine, and 39-bus system simulation. © 2023 IEEE.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Real-time Human Action Recognition using Deep Convolutional Neural Networks 15

Real-time Human Action Recognition using Deep Convolutional ...

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Vignesh, R. Balaraju, J. Poongothai, P. Rajput, Vaishali Rajkumar, N. Pratheep, V.G. Karunya Institute of Technology and Sciences Division of Artificial Intelligence and Machine Learning Karunya Nagar Coimbatore India Anuraag University Department of Cse Hyderabad India Department of Computer Science Bangalore India Vishwakarma Institute o Technology Computer engineering Pune India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Cse Thiruvalluvar Tamil Nadu Avadi India Kongu Engineering College Department of Mechatronics Engineering Tamil Nadu Perundurai638060 India

ISBN: (纸本)9798350370249

current advances in deep gaining knowledge of have enabled automated systems to understand human moves from movies in actual-time. Deep convolutional neural networks (DCNNs) had been used to allow accurate and efficient real-time movement reputation. with the aid of leveraging the statistics-driven illustration mastering capability of DCNNs, movement popularity has become a powerful device for video analysis applications including robotics, surveillance, entertainment, augmented truth, and healthcare. DCNNs use an aggregate of densely connected convolutional layers and in addition completely linked layers for function extraction from films. The proposed architectures are usually skilled using supervised learning. Convolutional layers are used to understand nearby abstractions in motion pictures, which in turn are used to research worldwide features. diverse techniques together with temporal segmentation, movement-based characteristic extraction, and feature switch gaining knowledge of are also hired by means of DCNNs for achieving higher performance. recent works have investigated exceptional techniques to enhance the accuracy and speed of action reputation the use of DCNNs. This consists of techniques which includes model compression, decoupled inference networks, and efficient convolutional networks. By using combining those strategies, it's far viable to acquire higher popularity accuracy at the same time as at the equal time preserving an excessive computational speed. © 2024 IEEE.

关键词： Computational Equal Excessive Gaining Research Speed

来源：评论

学校读者我要写书评

暂无评论

Metaheuristics for Financial Investment Strategies: Applications Survey

Metaheuristics for Financial Investment Strategies: Applicat...

引用

Electrical, computer, Communications and mechatronics engineering (ICECCME), International conference on

作者： Zineb Bousbaa Omar Bencharef Computer Science Department Computer and Systems Engineering Laboratory Faculty of Sciences and Technology Cady Ayyad University Marrakesh Morocco

Machine learning has been widely used as part of financial markets investment strategies, whether for forecasting the financial assets exchange rate, managing market volatility, or solving different classification problems that help with decision-making. Building an investment strategy using a scientific approach requires a massive amount of data, good computational power, and some expertise in the finance industry. Machine learning applications to the financial field, such as price exchange rate prediction, market pattern recognition, or other trading strategy tasks, are considered optimization problems. As they require an efficient algorithm dedicated to finding a global optimum, they can be solved using metaheuristics. In this survey, we study how metaheuristic optimization techniques contribute to building a robust learning model dedicated to financial investment strategy applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Autoencoders to Improve Classification of Online Arabic Handwriting: Addressing the Homogeneity Problem in Data 17

Using Autoencoders to Improve Classification of Online Arabi...

引用

17th International conference on Machine Vision, ICMV 2024

作者： Talib Alothman, Hasanien Ali Ameur, Safa Lejmi, Wafa Mahjoub, Mohamed Ali ISITCom - Higher Institute of Computer Science and Communication Technologies of Hammam Sousse University of Sousse Sousse4011 Tunisia University of Sousse Sousse4023 Tunisia Mechatronics Engineering Department College of Engineering University of Mosul Al Majmoaa Street Mosul41002 Iraq

ISBN: (纸本)9781510688278

The problem of heterogeneous datasets is considered one of the major challenges affecting deep learning efficiency, especially for the available online Arabic handwriting datasets. Most of the traditional methods used to enhance and manipulate dimensions do not amount to providing new data mimic real-world data. In this research, a novel method is presented using effective autoencoder networks to solve the problem of heterogeneous data. This is done by creating new data to fill the shortage of data. Autoencoder networks are a type of artificial neural network that can learn to represent data efficiently, which helps improve performance in classification tasks. It is also explained in detail how to perform data pre-processing, including the necessary steps to select and prepare the data that needs to be regenerated to ensure effective performance of autoencoder networks. The ADAB online Arabic handwriting dataset is used to evaluate the performance of our method by training and reconstructing input data using unsupervised learning. The autoencoder can recognize underlying patterns and create data more effectively. The experimental results show that using autoencoders reduces the effect of heterogeneity in the data and improves the accuracy of the classification models used. © 2025 SPIE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Construction of the RMST Indicator System for Aeronautical Complex Equipment Based on Correlation Analysis and Fuzzy-rough Set Theory 2

Construction of the RMST Indicator System for Aeronautical C...

引用

2022 2nd International conference on mechatronics Technology and Aerospace engineering, ICMTAE 2022

作者： Hu, Gexi Gong, Feng Liu, Hengchang Yao, Fengming Li, Bo School of Aeronautics and Astronautics University of Electronic Science and Technology of China China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province University of Electronic Science and Technology of China China

To solve the problem of the lack of a scientific indicator system in the current RMST research of complex aeronautical equipment, we focused on the construction principle of science and followed the six principles, including objective, complete, workable, independent, significant, and dynamic. We have adopted subjective methods to collect the RMST of indicators in all aspects. Then the redundant indicators with large correlation coefficients were eliminated sequentially using correlation analysis, and the indicators that did not have a significant impact on the evaluation results were eliminated using fuzzy rough set theory. In order to avoid the redundancy of indicators while ensuring the retention of significant indicators, a scientific and concise RMST indicator system was finally constructed, which filled the gap of the current RMST indicator system for aeronautical complex equipment. © Published under licence by IOP Publishing Ltd.

关键词： Rough set theory

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500页 << < 91 92 93 94 95 96 97 98 99 100 > >>

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：