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

18,409 篇 会议
217 册 图书
188 篇 期刊文献

馆藏范围

18,811 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

13,438 篇 工学
- 9,747 篇 计算机科学与技术...
- 6,612 篇 软件工程
- 3,603 篇 控制科学与工程
- 2,471 篇 信息与通信工程
- 2,304 篇 电气工程
- 1,741 篇 光学工程
- 1,517 篇 机械工程
- 1,118 篇 生物工程
- 909 篇 电子科学与技术（可...
- 864 篇 生物医学工程（可授...
- 785 篇 仪器科学与技术
- 574 篇 动力工程及工程热...
- 543 篇 交通运输工程
- 513 篇 安全科学与工程
- 499 篇 材料科学与工程（可...
- 454 篇 化学工程与技术
- 349 篇 土木工程
- 335 篇 网络空间安全
5,368 篇 理学
- 2,366 篇 物理学
- 2,288 篇 数学
- 1,231 篇 生物学
- 598 篇 统计学（可授理学、...
- 589 篇 系统科学
- 449 篇 化学
2,423 篇 管理学
- 1,722 篇 管理科学与工程(可...
- 830 篇 图书情报与档案管...
- 687 篇 工商管理
1,096 篇 医学
- 972 篇 临床医学
- 561 篇 基础医学(可授医学...
- 362 篇 药学(可授医学、理...
364 篇 法学
259 篇 经济学
253 篇 农学
218 篇 教育学
64 篇 军事学
25 篇 艺术学
20 篇 文学
3 篇 哲学

主题

1,582 篇 computer vision
370 篇 deep learning
314 篇 computer archite...
282 篇 cameras
255 篇 object detection
253 篇 computational mo...
237 篇 control systems
236 篇 computer science
220 篇 image segmentati...
211 篇 feature extracti...
209 篇 internet of thin...
187 篇 access control
173 篇 machine vision
158 篇 neural networks
137 篇 artificial intel...
133 篇 face recognition
130 篇 process control
130 篇 real-time system...
129 篇 data mining
128 篇 support vector m...

机构

47 篇 chitkara univers...
46 篇 school of comput...
43 篇 school of contro...
29 篇 maharishi school...
24 篇 karnataka bangal...
21 篇 school of comput...
19 篇 maharishi school...
17 篇 chitkara univers...
17 篇 college of compu...
15 篇 university of ch...
15 篇 school of comput...
14 篇 south china univ...
14 篇 dept. of compute...
14 篇 department of co...
14 篇 chitkara univers...
14 篇 college of compu...
13 篇 school of comput...
12 篇 school of comput...
12 篇 centre of interd...
12 篇 school of comput...

作者

19 篇 wang lei
18 篇 li yang
17 篇 wang wei
16 篇 yang yang
14 篇 liu yang
13 篇 wang hui
13 篇 ryszard tadeusie...
13 篇 marcin korytkows...
12 篇 wang ping
12 篇 wang jian
12 篇 sato jun
12 篇 jacek m. zurada
11 篇 zhang tao
11 篇 sakaue fumihiko
11 篇 zhang lei
11 篇 huang tinglei
11 篇 liu lei
10 篇 lei wang
10 篇 li xin
10 篇 wang jing

语言

16,844 篇 英文
1,863 篇 其他
133 篇 中文
16 篇 俄文
7 篇 西班牙文
2 篇 法文
2 篇 土耳其文

检索条件"任意字段=Proceedings of the 3rd International Conference on Control and Computer Vision"

共 18814 条记录，以下是4121-4130 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：

An Approach to Ensemble Simplified ResNet Models-Using Egyptian Hieroglyphs Data Set

An Approach to Ensemble Simplified ResNet Models-Using Egypt...

引用

Electronic Information Engineering and computer Science (EIECS), 2021 international conference on

作者： Zixiang Yan Kecheng Jin Jingkun Hou Pu Zhang College of Computer and Information Engineering (College of Artificial Intelligence) Nanjing Tech University Nanjing China Nanjing Hankai Academy Nanjing China School of Inteligence Science and Technology University of Science and Technology Beijing Beijing China Austin Friars St Monica's School Etterby Scaur Carlisle Cumbria UK

Since the inception of computer vision, recognizing text, including both printed and handwritten characters, has posed a significant challenge for traditional machine learning models. However, only a handful of these models have focused on ideographical scripts. Similarly, while mathematical solutions to common neural network problems such as degradation and computational complexity have been studied, possible shortcuts are often overlooked. This paper presents an innovative approach by introducing a novel ensemble network called "SparrowNet" and compares it to ResNet18 and GoogLeNet V2. Using an open-source Egyptian hieroglyph dataset, the paper focuses on evaluating the efficiency and accuracy of different networks using various performance metrics. Additionally, the paper discusses the advantages of the two existing models and explains the reasons behind the modifications made to SparrowNet. Through this research, it has been demonstrated that the use of 1x1 convolutions can significantly improve speed and reduce computational complexity, while a voting mechanism can be a novel solution to prevent degradation, and the modified network is capable to solve this particular character recognition task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Load Balancing Algorithm in Software Defined Networks 3

An Efficient Load Balancing Algorithm in Software Defined Ne...

引用

3rd international conference on Advances in Computing, Communication control and Networking, ICAC3N 2021

作者： Kumari, Shalini Kang, Sandeep Singh Chandigarh University Department of Computer Science and Engineering Mohali India

ISBN: (纸本)9781665438117

In a software-defined network, a network engineer or administrator can shape traffic from a centralized control console without having to touch individual switches in the network. A centralized SDN controller will direct the switches to deliver network services wherever they're needed, regardless of the specific connections between a server and devices. There is the need of an effective route to transfer data from devices to server. In order to set up this route, dynamic connectivity factor approach is used. Link failure in the network leads to the unbalancing of load in the network. This research work inducts the buffer size metric in the dynamic connectivity factor method to recover link, and eventually to balance the network load. When link failure occurs, the gadget having maximal buffer size will be opted for to recover link. The new strategy is enforced and compared against the dynamic connectivity factor method based on several metrics such as throughput, packet loss, delay and load balancing. © 2021 IEEE.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Models for Vocal Cords Detection in Laryngoscopic Imagery 28th

Application of Deep Learning Models for Vocal Cords Detectio...

引用

28th international conference on Knowledge Based and Intelligent information and Engineering Systems, KES 2024

作者： Vrba, Jan Steinbach, Jakub Cejnek, Matouš Jirsa, Tomáš Urbániová, Zuzana Department of mathematics informatics and cybernetics University of Chemistry and Technology in Prague Technická 5 Praha 6-Dejvice Prague166 28 Czech Republic Department of Instrumentation and Control Engineering Faculty of Mechanical Engineering Czech Technical University in Prague Technická 1902/4 Praha 6160 00 Czech Republic Department of Otorhinolaryngology 3rd Faculty of Medicine Faculty Hospital Královské Vinohrady Charles University Ruská 87 Praha 10 Prague100 00 Czech Republic

The accurate location of vocal cords is crucial in medical imaging applications for diagnostic and therapeutic purposes. In this study, we evaluated the performance of state-of-the-art object detection models, including the YOLO, EfficientDet D1, Faster RCNN and Single Shot Detector architectures, for the task of vocal cord detection. Using a data set of annotated medical images, we conducted comprehensive experiments to compare the models in terms of mean average precision (mAP) and inference time. Our results indicate that YOLOv8m achieved the highest performance, with a mAP@[0.5:0.95] of 0.778 and an inference time of 4.7 milliseconds. EfficientDet D1, Faster R-CNNs, and Single Shot Detectors trailed behind with slightly lower mAP scores. These findings highlight the efficacy of YOLOv8m for vocal cord localization on the utilized dataset. In addition, our study provides valuable information for the selection of suitable object detection models in medical imaging applications, facilitating better diagnosis and treatment planning in laryngology and otolaryngology. © 2024 The Authors.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Metabolite-disease Associations Prediction Based on Multi-kernel Learning and Graph Attention Networks 3

Metabolite-disease Associations Prediction Based on Multi-ke...

引用

3rd international conference on Image Processing, computer vision and Machine Learning, ICICML 2024

作者： Yang, Fuyang Wang, Jiajia Su, Ying Lv, Xiaoyi Xinjiang University College of Computer Science and Technology Urumqi830046 China Xinjiang University Xinjiang Aqisd Testing Technology Co Urumqi830063 China Xinjiang University College of Software Urumqi830046 China

ISBN: (纸本)9798350355413

A growing number of scholars have confirmed through research that there is a strong correlation between changes in metabolite levels in the human body and various complex diseases. In this study, we propose a new framework (MKLGAT-MDA) that integrates multi-kernel learning and graph attention network (GAT) for enhanced metabolite-disease associations prediction. First, the study employs multi-kernel learning to combine different similarity matrices to capture feature information from different perspectives of metabolites and diseases. Then a GAT network with a path-learning graph space operator is employed to generate meaningful spatial convolutions from the paths in GAT to improve the prediction performance. The average AUC at 5-cv is 0.9562 and the average AUPR is 0.9575. The experimental findings indicate that our model surpasses current methods regarding prediction accuracy and reliability. © 2024 IEEE.

关键词： Metabolites

来源：评论

学校读者我要写书评

暂无评论

Voice Feature Analysis for Speaker Recognition to Improve Content Management 3

Voice Feature Analysis for Speaker Recognition to Improve Co...

引用

3rd international conference on Advances in Computing, Communication control and Networking, ICAC3N 2021

作者： Moondra, Amit Chahal, Poonam Manav Rachna International Institute of Research and Studies Faculty of Engineering Department of Computer Science Engineering Faridabad India

ISBN: (纸本)9781665438117

We are introducing feature extraction approach which helps in content control on broadband television. Speaker recognition-based content control are more effective as compare to traditional permission-based method. Television content can be controlled based on the program requester's age and program requester's age can be identified based on his/her voice. Speaker is adult or not that can be identified based on his/her voice. Every person's voice is unique based on voice features like pitch, frequency, jitter, amplitude, and spectral power. This article explains how we can effectively use these features to classify child and adult voice. In general, Mel-Frequency Cepstral Coefficient (MFCC) is used for effective feature extraction and it provides features' numerical values. Artificial Intelligence (AI) based system uses these features for accurate speaker recognition. Child and adult voice can be differentiate at time, frequency, mel scale level, which can help for clear classification of the speaker. Power spectrum and mel-spectrum also represent difference in child and adult voice. © 2021 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Rice Leaf Disease Detection Using Deep Learning Models: A Comprehensive Approach 3

Rice Leaf Disease Detection Using Deep Learning Models: A Co...

引用

3rd international conference on Disruptive Technologies, ICDT 2025

作者： Ramya, Gorli Vatsavayi, Valli Kumari Andhra University College of engineering Department Of Computer Science And Systems Engineering Visakhapatnam530003 India

ISBN: (纸本)9798331519582

Rice serves as a primary food source for more than half of the global population. However, a range of diseases brought on by pathogens, including as bacteria, viruses and fungus are posing a growing threat to rice agriculture. These diseases have the potential to seriously reduce crop productivity and threaten food security. Conventional disease detection techniques mostly depend on the labor-intensive, time consuming and frequently prone to human error manual inspection performed by qualified agronomists. We concentrate on two cutting edge architectures: vision Transformers (ViT) and DenseNet169, which is well-known for its high accuracy in image classification applications and efficiency in feature reuse which make use of self-attention mechanisms to identify complex patterns in images. We developed these models to precisely categorize various rice leaf diseases, including Bacterial Leaf Blight, Brown Spot, Leaf Blast, Leaf Scald, Narrow Brown Spot, Neck Blast, Rice Hispa, Sheath Blight, Tungro, and healthy leaves. This was achieved using a comprehensive dataset containing 15,910 annotated images of rice leaves. Our proposed systems improve crop management practices by enabling prompt interventions based on precise predictions but it helps to guarantee ensuring global food security and maximizing overall crop yield. This study highlights the revolutionary potential of artificial intelligence in agriculture, paving the way for further advancements that can enhance sustainability and productivity. © 2025 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaption based on metric learning for Person Re-Identification 3

Unsupervised Domain Adaption based on metric learning for Pe...

引用

2021年第三届先进计算机技术、信息科学与通信国际会议(CTISC2021)

作者： Roolmich Pierre Meibin Qi Computer Science Department Hefei University of Technology

ISBN: (纸本)9781665418683

Person re-identification(ReID) with deep convolutional neural networks(CNNs) has attracted increasing interest in computer vision due to its wide potential applications in visual surveillance and has achieved high performance in recent years using a lot of techniques to overcome the challenges such as variations in view angle, lighting, image occlusion. Another main challenge in person re-identification(ReID) is the cross domain *** to different domains, a person re-identification model trained on one dataset with good performance often fails to achieve same or better performance on other datasets. We propose a method which is about both the source and target datasets. We fine-tune the deep CNN model on the labeled source dataset in a supervised manner by using distance metric learning and the unlabeled target dataset in an unsupervised manner simultaneously.

关键词： Measurement Adaptation models Visualization Information science computer vision Surveillance Memory management

来源：评论

学校读者我要写书评

暂无评论

An experimental teaching platform for machine vision-based real-time detection taking quality inspection of paper cups as instance

An experimental teaching platform for machine vision-based r...

引用

Educational Technology (ICET), IEEE international conference on

作者： Yanzhe Huang Yabo Luo Xiangyu Zhou School of Mechanical and Electronic Engineering Wuhan University of Technology Wuhan China

In order to improve the quality of students' practical training, a real-time detection system experimental platform based on machine vision has been designed. The system has functions of real-time sampling, detection, defective product removal, result display and data storage, and its structure covers three parts: hardware platform, detection algorithm, and software function implementation. The hardware platform includes image acquisition module, material transportation module and defective product removal module, and the control circuit is based on the development of Arduino and STM32. The detection algorithm is developed based on OPENCV, and it is designed to detect three types of defects: cup rim concavity, cracking, and out-of-roundness. The software system is jointly developed using Visual Studio 2019 and Qt Creator 4.9.1, and it has good interactivity. With this experimental platform, teaching work such as image acquisition system construction, dynamic sampling problem analysis, image detection algorithm development, and interactive interface implementation can be carried out, so as to improve students' engineering design ability in many aspects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

All You Need Is Superword-Level Parallelism: Systematic control-Flow Vectorization with SLP 2022

All You Need Is Superword-Level Parallelism: Systematic Cont...

引用

43rd ACM SIGPLAN international conference on Programming Language Design and Implementation (PLDI)

作者： Chen, Yishen Mendis, Charith Amarasinghe, Saman MIT 77 Massachusetts Ave Cambridge MA 02139 USA Univ Illinois Urbana Chamaign Urbana IL USA

ISBN: (纸本)9781450392655

Superword-level parallelism (SLP) vectorization is a proven technique for vectorizing straight-line code. It works by replacing independent, isomorphic instructions with equivalent vector instructions. Larsen and Amarasinghe originally proposed using SLP vectorization (together with loop unrolling) as a simpler, more flexible alternative to traditional loop vectorization. However, this vision of replacing traditional loop vectorization has not been realized because SLP vectorization cannot directly reason with control flow. In this work, we introduce SuperVectorization, a new vectorization framework that generalizes SLP vectorization to uncover parallelism that spans different basic blocks and loop nests. With the capability to systematically vectorize instructions across control-flow regions such as basic blocks and loops, our framework simultaneously subsumes the roles of inner-loop, outer-loop, and straight-line vectorizer while retaining the flexibility of SLP vectorization (e.g., partial vectorization). Our evaluation shows that a single instance of our vectorizer is competitive with and, in many cases, significantly better than LLVM's vectorization pipeline, which includes both loop and SLP vectorizers. For example, on an unoptimized, sequential volume renderer from Pharr and Mark, our vectorizer gains a 3.28x speedup, whereas none of the production compilers that we tested vectorizes to its complex control-flow constructs.

关键词： optimization auto-vectorization

来源：评论

学校读者我要写书评

暂无评论

Research on Closed-loop control of Friction Stir Welding Robot Based on Ultrasonic Positioning 3

Research on Closed-loop Control of Friction Stir Welding Rob...

引用

3rd international conference on Artificial Intelligence and Electromechanical Automation, AIEA 2022

作者： Wan, Qiang Zhou, Zhipeng Xiong, Zheng Institute of Mechatronics and Automation Wuchang Shouyi University Wuhan China

ISBN: (纸本)9781510657281

A heavy-duty industrial robot with a load of 3.5kn and a positioning accuracy of 0.05mm was combined with the end effector of friction stir welding and refitted into a robot friction stir welding system. In the friction stir welding machining test, it was found that although the structural strength of the robot met the use requirements, its stiffness under some working conditions didn’t meet the requirements, resulting in low positioning accuracy and unsatisfactory machining accuracy of the friction stir welding robot. To solve this problem, a closed-loop controlled heavy-duty friction stir welding robot system based on ultrasonic positioning technology was designed. The system was composed of dual ultrasonic transmitters, multiple ultrasonic receivers, positioning processor. Two ultrasonic transmitters with different transmission frequencies were arranged at two different positions of the end effector, and then two groups of receivers that could distinguish the ultrasonic frequency were used to receive the ultrasonic signal. The real-time coordinates of the two ultrasonic transmitters in the positioning space were calculated by the positioning system to determine the position and posture of the end effector. The end effector was controlled to track the predetermined trajectory in real time to realize the closed-loop control of the robot. Based on the three-point positioning principle, the relevant calculation and analysis were carried out, which proved the rationality and feasibility of the system in theory. The experimental results show that the positioning accuracy of the system is within 1mm and the posture error is within 0.01◦. © 2022 SPIE.

关键词： Friction stir welding

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 << < 409 410 411 412 413 414 415 416 417 418 > >>

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：