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

959 篇 会议
3 篇 期刊文献

馆藏范围

962 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

447 篇 工学
- 371 篇 计算机科学与技术...
- 336 篇 软件工程
- 116 篇 信息与通信工程
- 104 篇 生物工程
- 77 篇 生物医学工程（可授...
- 51 篇 电气工程
- 46 篇 控制科学与工程
- 35 篇 电子科学与技术（可...
- 35 篇 化学工程与技术
- 32 篇 光学工程
- 26 篇 安全科学与工程
- 25 篇 交通运输工程
- 23 篇 农业工程
- 22 篇 动力工程及工程热...
- 20 篇 建筑学
240 篇 理学
- 109 篇 数学
- 106 篇 生物学
- 50 篇 物理学
- 46 篇 统计学（可授理学、...
- 45 篇 系统科学
- 36 篇 化学
139 篇 管理学
- 83 篇 图书情报与档案管...
- 69 篇 管理科学与工程(可...
- 41 篇 工商管理
48 篇 医学
- 48 篇 临床医学
- 42 篇 基础医学(可授医学...
- 31 篇 药学(可授医学、理...
37 篇 法学
- 28 篇 社会学
27 篇 农学
- 26 篇 作物学
20 篇 经济学
- 20 篇 应用经济学
8 篇 教育学
2 篇 军事学

主题

157 篇 data engineering
129 篇 computer science
95 篇 conferences
75 篇 computational mo...
57 篇 data models
48 篇 predictive model...
47 篇 deep learning
45 篇 machine learning
44 篇 training
37 篇 feature extracti...
34 篇 neural networks
24 篇 support vector m...
24 篇 machine learning...
22 篇 covid-19
21 篇 computer archite...
18 篇 education
18 篇 visualization
18 篇 prediction algor...
17 篇 social networkin...
17 篇 industries

机构

10 篇 queensland unive...
9 篇 brac university ...
8 篇 school of comput...
8 篇 graduate school ...
7 篇 brac university ...
7 篇 school of comput...
7 篇 computer science...
7 篇 school of comput...
6 篇 department of co...
6 篇 school of engine...
6 篇 college of infor...
6 篇 school of comput...
5 篇 brac university ...
5 篇 school of inform...
5 篇 school of food a...
5 篇 doshisha univers...
5 篇 department of co...
5 篇 university of as...
5 篇 graduate school ...
5 篇 school of scienc...

作者

17 篇 neeraj anand sha...
12 篇 md. golam rabiul...
11 篇 sharma neeraj an...
11 篇 bibhya sharma
10 篇 md. ashraful ala...
9 篇 alam md. golam r...
9 篇 richard o. sinno...
9 篇 katsunori shimoh...
9 篇 shimohara katsun...
9 篇 a b m shawkat al...
8 篇 sharma bibhya
8 篇 girija chetty
7 篇 ryo shioya
7 篇 tanaka mizuki
7 篇 shioya ryo
7 篇 shiozu yurika
7 篇 hiromitsu shimak...
7 篇 kunal kumar
7 篇 alam md. ashrafu...
7 篇 mizuki tanaka

语言

950 篇 英文
12 篇 其他

检索条件"任意字段=2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2022"

共 962 条记录，以下是341-350 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：

PRODG: Practical Overlapping Community Detection in Weighted Graphs using Deep GCNs

PRODG: Practical Overlapping Community Detection in Weighted...

引用

computer science and data engineering (csde), ieee asia-pacific conference on

作者： Md Nurul Muttakin Muhammad Anwarul Azim Md Iqbal Hossain Md. Saidur Rahman Department of Computer Science and Engineering Graph Drawing & Information Visualization Lab Bangladesh University of Engineering and Technology Dhaka - 1205 Bangladesh Research Innovation & Impact (RII) The University of Arizona Tucson Arizona USA

Graph-based neural networks, including transformers, are the most used neural networks. Recently, overlapping community detection problems have been tackled using graph convolutional networks (GCN), achieving superior performance than classical methods. However, some of these methods have limited practical use as they require ground truth information to optimize the hyper-parameters. In addition, most existing works, including GCN-based methods, either ignore the edge weight of weighted graphs or fail to leverage the edge weight information to achieve better performance. To this end, we propose PRODG as a practical overlapping community detection method in edge-weighted graphs using deep GCNs. Specifically, we design weighted dilated aggregation algorithms to incorporate the information of edge weights to achieve a deep-weighted residual GCN (WResGCN) model. Moreover, we perform a completely unsupervised modularity-based depth search for deep GCNs, making our method available for practical applications. We apply our model to real-world Facebook graphs with synthetic edge weights, having reliable ground truth information. Experimentation and evaluation show that our methods effectively leverage the edge-weight in weighted graphs. Our completely unsupervised depth search strategy in deep GCNs performs competitively or better than state-of-the-art methods, bolstering the practical use of deep GCNs in overlapping community detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Messages for Improvement of walking amount based on a stage of change

Messages for Improvement of walking amount based on a stage ...

引用

computer science and data engineering (csde), ieee asia-pacific conference on

作者： Rintaro Kataoka Hiromitsu Shimakawa Fumiko Harada Graduate School of Information Science and Engineering Ritsumeikan University Shiga Japan College of Information Science and Engineering Ritsumeikan University Shiga Japan Research Organization of Science and Technology Ritsumeikan University Shiga Japan

Based on the transtheoretical model of how be-havior change occurs, this study proposes a support to in-crease the amount of walking through messages. In recent years, lifestyle-related diseases have been threatening people's life expectancy. Regular exercise can prevent lifestyle-related dis-eases. However, currently one in four adults does not get enough exercise. It is not easy to improve the habit of inactivity, and some kind of intervention is required to promote behavioral change. In the transsexual model, which is a model of behavior change, effective interventions differ depending on the stage of change, the transformation stage. In this study, the stage of change is estimated based on the data of the number of steps taken after the intervention with messages. We examine step count data with and without intervention, and with different types of intervention. Seasonal and exogenous components of the step count data were eliminated by the SARIMAX model. In a 6-week experiment with 14 university students and adults, we found that the intervention of e-mail messages could increase the subjects' motivation to exercise. However, it was not possible to identify the types of effective messages for each stage of change.

关键词： Legged locomotion computer science Computational modeling data engineering data models Behavioral sciences Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Automated Assessment of Excessive Inbreeding of Dogs based on Deep Learning

Automated Assessment of Excessive Inbreeding of Dogs based o...

引用

computer science and data engineering (csde), ieee asia-pacific conference on

作者： Yanmin Liu Richard O. Sinnott School of Computing and Information Systems University of Melbourne Melbourne VIC Australia

Brachycephalic obstructive airway syndrome (BOAS) is a common disease that effects animals such as bulldogs and Persian cats,resulting from excessive inbreeding to produce an idealized pet. The physical manifestations of BOAS are a flat to concave face, smaller nostrils and excessive wrinkles. Unfortunately, BOAS has a range of negative impacts on the dogs,causing some problems themselves including skin irritation, breathing difficulties and a reduced lifespan. In this paper we explore the extent to which BOAS can be automatically quantified through deep learning. A range of deep learning models were explored including MLP, CNN, VGG16, VGG16 fine-tuning (later 3 layers), Xception, and Xception fine-tuning (later 33 layers) on a data set that was established for the work. Experiences and results of the application of the different deep learning approaches are presented.

关键词： Deep learning Neural networks Dogs Predictive models Feature extraction data models Skin

来源：评论

学校读者我要写书评

暂无评论

Modelling of Tsunami Wave Generated by Volcanic EruptionUsing Impulsive Disturbance for 2022, Tonga Island Tsunami 8

Modelling of Tsunami Wave Generated by Volcanic EruptionUsin...

引用

8th International conference on data science and Machine Learning Applications, CDMA 2025

作者： Syed Mohamed, E. Yasmin Regina, M. B. S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai600048 India B. S. Abdur Rahman Crescent Institute of Science and Technology Department of Civil Engineering Tamil Nadu Chennai600048 India

ISBN: (纸本)9798331539696

Tsunamis caused by volcanic eruptions have received less research, because of the intricacy of the generation and the rarity of their occurrence in the past. Frequency of occurrence of a volcanic event in the pacific Rim and the ensuing harm to mankind, it is now vital to forecast the genesis and behavior of tsunamis caused by volcanic eruptions to avoid catastrophic destruction. Tsunami generation is modelled in this study using the eruption's impulse force and a flow rate comparison between the erupted materials and the seawater. The initiated tsunami wave propagation height is computed using the energy of displaced seawater, and the tsunami propagation phase is modelled using the Boussinesq approximation and solitary wave theory. The tsunami's phases are modelled for the Hunga Tonga-Hunga Ha'apai volcanic eruption event in 2022, and the tsunami wave characteristics are projected to reach Nuku'alofa, Tonga's capital city. The wave height and travel time of the tsunami reaching the coast of Nuku'alofa are calculated as 0.8338 m and 19 minutes 34 seconds, therefore the tsunami hit Nuku'alofa at 04:46:34 UTC. © 2025 ieee.

关键词： Tsunamis

来源：评论

学校读者我要写书评

暂无评论

Disclosing Features and Characteristics of. COM Registrars' WHOIS Servers 2

Disclosing Features and Characteristics of. COM Registrars' ...

引用

2nd asia-pacific conference on Communications Technology and computer science, ACCTCS 2022

作者： Cheng, Yanan Liu, Yali Piao, Guanhua Zhang, Zhaoxin Li, Ning Qiu, Mingyu Harbin Institute of Technology Faculty of Computing Department of Computing Harbin China

ISBN: (纸本)9781665400343

The number of top-level domain names(.COM) registrars has long been dominant in the world's domain name resources. Still, few relevant documents have made specific analyses and statistics on the characteristics of. COM registrars. In this context, for the first time, we conducted a large-scale detection study on the WHOIS server of the. COM registrar. This article analyzes the characteristics of the. COM registrar from five aspects: the relationship between the world's top. COM registrar and the server and IP;the relationship between the IP address of the WHOIS server and the WHOIS server;nonexistent domain names response to different messages;abnormalities of WHOIS server;distribution of GDPR. In this article, through large-scale detection and analysis of the WHOIS server of the. COM registrar, we can intuitively see the relevant data of the WHOIS server. The COM registrar discovers the vital relationship between the registrar, server, and IP. The research on the direction of the WHOIS server of the. COM registrar provided by scientific researchers has played a perfect guiding role. © 2022 ieee.

关键词： computer science Communications technology Servers IP networks Security

来源：评论

学校读者我要写书评

暂无评论

Plant Leaves Classification System

Plant Leaves Classification System

引用

computer science and data engineering (csde), ieee asia-pacific conference on

作者： Rasendram Muralitharan Nilani Inuvaisubramaniam Upul Jayasinghe Roshan G Ragel Aarumuham Rajeevan Gramma Niladhari Department of Computer Engineering Faculty of Engineering University of Peradeniya Sri Lanka Office of the Deputy Chief Secretary-Engineering Northern Province Sri Lanka Divisional Secretariat Uduvil Sri Lanka

Plant leaves could be classified using machine learning techniques. The plant leaves could be used to identify the different types of the plants. Lot of plant leaves classification systems are developed using machine learning techniques. Support Vector Machine, Random Forest, K Nearest Neighbour, and Convolutional Neural Network algorithms could be used to develop the plant leaves classification systems. Colour, Shape, Texture, and Vein details could be used as the features to classify the plant leaves. Though we have lot of plant leaves classification systems, the accuracy of the classification systems is low. We use the shape, and the colour of the plant leaves as features to classify the plant leaves. We have collected the length, width, and colour data from five different plants, which are Jack fruit, Lemon, Nochi, Guava, and Cinnamon. Nearly fifty samples are collected from each type of the plant. Our classification system uses machine learning algorithms to identify the plants. The system uses K Nearest Neighbour, Support Vector Machine, and Random Forest algorithms. The system could be used to classify plant leaves in the agricultural industry, and Ayurvedic medicine industry. The accuracy, precision, recall, and F1 score of the models are obtained. We have achieved the highest prediction accuracy of 99% in the Random Forest algorithm. The local pattern of the plant species could be found in the first layer of the convolutional neural network model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation study and optimal design of a new microstrip quasi-Yagi antenna for WiFi frequency band applications 2

Simulation study and optimal design of a new microstrip quas...

引用

2nd asia-pacific conference on Communications Technology and computer science, ACCTCS 2022

作者： Li, Dianyuan Li, Aifeng Yang, Guangkuo Xu, Chongqi Shandong Agricultural University College of Information Science and Engineering Tai'an China

ISBN: (纸本)9781665400343

This paper proposes a new microstrip quasi-Vagi antenna for WiFi band applications. The antenna structure employs an E-type reflector as well as 8 split-ring resonators, which makes the quasi-Vagi antenna with high gain and wide bandwidth to meet the requirements of wireless communication. Ansys simulation is used to model and analyze the gain, return loss and radiation direction characteristics of the antenna. Finally, the new microstrip quasi-Yagi is obtained, which has the largest gain of 7.28dB and can work at 2.32-2.66GHz with a relative bandwidth of 14%, covering the WiFi band. The antenna has a simple structure, easy to use, low cost, is powerful, and has good practical application value in projects with a large demand for antenna directional gain. © 2022 ieee.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Frame Elimination for Recordings of Bat Flight Kinematics from a High-Speed Video Array

Frame Elimination for Recordings of Bat Flight Kinematics fr...

引用

computer science and data engineering (csde), ieee asia-pacific conference on

作者： D.P. Jayathunga M. Ramashini Juliana Zaini Liyanage C. De Silva R. Müller Department of Computer Science and Informatics Uva Wellassa University of Sri Lanka Sri Lanka Faculty of Integrated Technologies Universiti Brunei Darussalam Brunei Darussalam School of Digital Science and Faculty of Integrated Technologies Universiti Brunei Darussalam Brunei Darussalam Department of Mechanical Engineering Virginia Tech Blacksburg USA

Bat flight is complex because they have the ability to change the shape of their wings while in flight to perform manoeuvres. To accurately capture the subject's complexity, we have set up a synchronized array of $50\text{high}$ -speed cameras. This array is capable of capturing over 50,000 images per second. The video array is designed to cover a large imaging volume that allows bats to perform full-flight manoeuvres. As a result, many video frames do not show the entire bat. Hence, this study uses deep learning techniques to develop an accurate frame elimination process. Until the controlled environment is set up, we used simulated data created from the blender. For the frame elimination purpose, images needed to be classified based on the location of the bat, where it could be fully or partially presented within the frame or maybe not presented. We used different deep learning techniques, including the ordinary CNN, pretrained models, and object detection model - YOLOv5, to achieve this target. Among all the models, we noted that YOLOv5 gave the best accurate unwanted frame elimination results, where the mAP0.5 value is 0.99 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

data vault modelling as alternative to dimensional modelling to embrace complexity in data driven decision systems: a critical systems perspective

Data vault modelling as alternative to dimensional modelling...

引用

computer science and data engineering (csde), ieee asia-pacific conference on

作者： Roelien Goede Unit for Data Science and Computing North-West University Potchefstroom South Africa

We live in a complex world where uncertainty is the only certainty. Today's compelling business problem is replaced tomorrow with a problem which was not even imagined yesterday. data driven decision systems are used by managers in support of their strategic decisions and should be agile and flexibility to survive in our ever change world of complex decisions. The argument presented in this conceptual paper is that data vault modeling is inherently better equipped than dimensional modelling to handle the turbulations of our complex world. The paper investigates the underlying assumptions of dimensional modelling and data vault modelling in terms of requirements collection and the resulting data modelling techniques. It uses critical systems thinking as guiding philosophy to reflect on the benefits of understanding and modelling a variety of perspectives in a problem situation. Critical systems thinking also promotes equal opportunity and accountability. It is argued that both these aspirations can better be achieved by using dimensional modeling as alternative to dimensional modelling. We hope to promote the development of sustainable data driven decision systems which can stand the test of our turbulent times.

关键词： computer science Uncertainty Philosophical considerations Computational modeling data engineering data models Equal opportunities

来源：评论

学校读者我要写书评

暂无评论

Research on relation extraction method of contract text based on BERT 2

Research on relation extraction method of contract text base...

引用

2nd asia-pacific conference on Communications Technology and computer science, ACCTCS 2022

作者： Chang, Yuan Kong, Lei Meng, Qinglei 2nd Institute of China Aerospace Science and Industry Corporation Aerospace Science and Industry Network Information Development Co. Ltd Beijing China Aerospace Science and Industry Network Information Development Co. Ltd Beijing China

ISBN: (纸本)9781665400343

Entity recognition and relation extraction techniques in text mining are very important for the extraction of sensitive information in contract texts. Due to the lack of corpus in the field of contract texts, and the existing entity relation extraction models cannot extract relationships based on the semantics of contract texts. In view of the above problems, in order to enable the relation extraction model to apply the domain characteristics and domain knowledge of the contract domain, this paper proposes a joint entity-relation extraction method that integrates the representation of contract features, and incorporates the dictionary features into the model encoder part through the self-attention mechanism. The experimental results show that the learning of entity relationship information interaction and the introduction of the fusion contract type feature encoder can effectively improve the model performance. © 2022 ieee.

关键词： Domain Knowledge

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97页 << < 31 32 33 34 35 36 37 38 39 40 > >>

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：