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

1,022 篇 会议
7 篇 期刊文献
5 册 图书

馆藏范围

1,034 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

795 篇 工学
- 710 篇 计算机科学与技术...
- 624 篇 软件工程
- 214 篇 生物工程
- 171 篇 信息与通信工程
- 122 篇 生物医学工程（可授...
- 85 篇 控制科学与工程
- 65 篇 光学工程
- 58 篇 机械工程
- 53 篇 化学工程与技术
- 47 篇 电气工程
- 37 篇 材料科学与工程（可...
- 26 篇 安全科学与工程
- 25 篇 电子科学与技术（可...
433 篇 理学
- 227 篇 生物学
- 205 篇 数学
- 98 篇 系统科学
- 79 篇 物理学
- 70 篇 统计学（可授理学、...
- 35 篇 化学
208 篇 管理学
- 131 篇 图书情报与档案管...
- 99 篇 管理科学与工程(可...
- 48 篇 工商管理
109 篇 医学
- 105 篇 临床医学
- 102 篇 基础医学(可授医学...
- 86 篇 药学(可授医学、理...
- 30 篇 公共卫生与预防医...
85 篇 教育学
- 84 篇 教育学
48 篇 法学
- 45 篇 社会学
26 篇 农学
- 24 篇 作物学
23 篇 经济学
- 23 篇 应用经济学
3 篇 军事学
2 篇 文学

主题

167 篇 machine learning
72 篇 deep learning
32 篇 support vector m...
32 篇 machine learning...
30 篇 education
28 篇 training
27 篇 students
24 篇 learning algorit...
21 篇 feature extracti...
21 篇 convolutional ne...
20 篇 computational mo...
18 篇 neural networks
18 篇 decision trees
17 篇 covid-19
17 篇 artificial intel...
17 篇 forecasting
16 篇 predictive model...
15 篇 learning systems
15 篇 data mining
15 篇 computer vision

机构

21 篇 department of co...
6 篇 department of co...
4 篇 nanchang vocatio...
3 篇 natural sciences...
3 篇 department of en...
3 篇 school of comput...
3 篇 daffodil interna...
3 篇 international sc...
3 篇 college of infor...
3 篇 school of inform...
3 篇 department of ma...
3 篇 computer and inf...
2 篇 beijing normal u...
2 篇 university of sc...
2 篇 college of compu...
2 篇 department of bu...
2 篇 wuxi institute o...
2 篇 graphic era univ...
2 篇 jinan university...
2 篇 college of compu...

作者

5 篇 pravin a.
4 篇 nagarajan g.
4 篇 prem jacob t.
3 篇 pereira ana i.
3 篇 zhang bo
3 篇 yan li
3 篇 bilgaiyan saurab...
3 篇 zolkin a.l.
3 篇 munister v.d.
3 篇 zhang xin
3 篇 yang jie
3 篇 wang lin
2 篇 gupta shagun
2 篇 dehuri satchidan...
2 篇 singh ashutosh k...
2 篇 lima jose
2 篇 mishra bhabani s...
2 篇 bhuiyan mohammad...
2 篇 zhang lei
2 篇 zhang song

语言

1,025 篇 英文
9 篇 其他
2 篇 中文

检索条件"任意字段=2021 2nd International Conference on Machine Learning and Computer Application, ICMLCA 2021"

共 1034 条记录，以下是991-1000 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：

Research on the posture recognition method of suckling sow based on deep learning

Research on the posture recognition method of suckling sow b...

引用

Intelligent Computing and Human-computer Interaction (ICHCI), international conference on

作者： Fang Li Qiuju Xie Weizhan Shi College of Computer Science and Software Zhaoqing University Zhaoqing Guangdong

ISBN: (纸本)9781665407656

The posture of the sow is one of the important evaluation indicators of its maternal behavior, so it has received extensive attention from breeding and breeding management. At present, the recognition of the sow's posture is mostly based on machine vision and three-axis acceleration sensors. However, when using machine vision technology to capture individual posture images of pigs in the rearing state, the efficiency of sow posture recognition is low due to factors such as light intensity, complexity of the environment in the pen, and location of the pigs. In this paper, 18 postpartum Dumin (Dulac × Min pigs) sow postures were collected for 8 days of video data, and the sow posture recognition model was established based on the Dual-Resnet34 method. Offline and online data enhancement methods are used to enhance the captured image and efficiently decouple the posture features to improve the efficiency of model training. A dual-channel residual network combined with a large convolution kernel is proposed to linearly determine the pig features, which improves the accuracy of the model. The results show that the model proposed in this paper has a positive rate of 99.68%, 99.99%, 99.06%,99.5%, and 99.99% for the 5 types of postures of lactating sows on the test set. And the overall recognition rate of various gestures of pigs reaches 99.5%, which is an increase of 0.42% compared to the single-channel Resnet34. Therefore, this method improves the recognition accuracy while ensuring the recognition efficiency, which can provide a technical reference for the automatic recognition of sow behavior.

关键词： Training Image recognition Target recognition Convolution machine vision Data models Sensors

来源：评论

学校读者我要写书评

暂无评论

Implementation of machine learning for Sentiment Analysis of Social and Political Orientation in Pekanbaru City 2

Implementation of Machine Learning for Sentiment Analysis of...

引用

2020 2nd international conference on Enhanced Research and Industrial application 2020

作者： Indra, Zul Setiawan, Azhari Jusman, Yessi Department of Informatics Engineering Faculty of Engineering Universitas Abdurrab Pekanbaru Riau28291 Indonesia Department of International Relations Faculty of Social and Political Sciences Universitas Abdurrab Pekanbaru Riau28291 Indonesia Department of Electrical Engineering Faculty of Engineering Universitas Muhammadiyah Yogyakarta Bantul Daerah Istimewa Yogyakarta55183 Indonesia

Nowadays, people are free to express their opinions regarding a problem in online social networks. One of most popular social network used to express opinions is Twitter. Public opinion in online social network has become a new source of big data that is interesting to be investigated. Opinion expressed by the public through social media is valuable data that can be further processed by using natural language processing (NLP). This research is expected to explain the social, economic, and political orientation of the people of Pekanbaru city by utilizing NLP algorithm. In addition, in terms of data sources, similar research is dominated by national studies, a little local. This research used Sentiment Analysis of Natural Language Processing (NLP) algorithm to analyze Pekanbaru citizen's views and perceptions about social and political issues. The methods consist of: (i) data collection, (ii) data preprocessing, and (iii) sentiment classification. Thousands of tweets were extracted from Twitter API platform as research samples. As a result, the research has obtained 833 tweets about social orientation and 156 tweets about political trends. Overall, our tweets mined data were dominated with positive sentiments (53%). Education was the topic with most positive sentiments (42%) while political figure was the topic with most neutral sentiments (65%) and environment was the topic with most negative sentiments (56%). Regarding the discourses, "sampah"(garbage, waste, trash, etc) was the most posted and discussed in Twitter along with floods and air pollution topics. © Published under licence by IOP Publishing Ltd.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Combining Minimal Surface Model with DGCNN for Natural Language Understanding

Combining Minimal Surface Model with DGCNN for Natural Langu...

引用

international conference on Electronics, Communications and Information Technology (CECIT)

作者： Mingkai Zha Gongqi Lin Hongguang Fu Yunhao Liu Lei Huang University of Electronic Science and Technology of China Chengdu China Chinese Academy of Sciences Chengdu Institute of Computer Application Chengdu China

ISBN: (纸本)9781665437585

Fine-tuning large pre-trained models is an adequate transfer mechanism in Natural Language Processing (NLP). However, it is challenging to serve in resource-restricted devices due to being computationally expensive. To reduce the trainable parameters of models while maintaining accuracy, we propose a novel geometry deep learning approach named Minimal Surface Model on DGCNN (MSM-D). In MSM-D, the minimal surface model is introduced as an adapter layer to convert the word vector into high-dimensional manifold data, an input to the point cloud model. MSM - D is empirically adequate and achieves close or even better performance of BERT-base on GLUE benchmark while being 5.7x smaller on inference.

关键词： Point cloud compression Manifolds Geometry Deep learning Adaptation models Computational modeling Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Preliminary Investigation into machine-Learned 2D Automated Video Surveillance Systems

Preliminary Investigation into Machine-Learned 2D Automated ...

引用

international Carpathian Control conference (ICCC)

作者： Adam Surówka Faculty of Electrical and Computer Engineering Cracow University of Technology Kraków PL

The purpose of this study is to explore the possibility of using 2D human pose estimation algorithms in automated video surveillance systems. The proposed concept boils down to develop an intelligent application that can handle the incoming results and even prevent the occurrence of critical events in the monitored areas. The so-called critical events represent the acts of vandalism, crime, burglary, theft, fights, etc. The core aspect of the described solution is the use of conventional 2D imaging devices, i.e. CCTV cameras, IP webcams or even mobile phone cameras and an AI (artificial intelligence) neural network trained on a set of images. That makes the proposed solution relatively cheap, universal and easy to install across a wide range of target environments without the need for additional sensors. In the paper the authors highlights the architecture of the system, presents details of the video data acquisition stage followed by a description of the 2D human pose estimation toolkit. It is then complemented by summarizing the data extraction stage from pre-recorded clips for machine learning.

关键词： Webcams Pose estimation Data acquisition machine learning Video surveillance Mobile handsets IP networks

来源：评论

学校读者我要写书评

暂无评论

SinGlow: Singing Voice Synthesis with Glow: Help Virtual Singers More Human-like

SinGlow: Singing Voice Synthesis with Glow: Help Virtual Sin...

引用

Artificial Intelligence and computer Engineering (ICAICE), international conference on

作者： Haobo Yang School of Informatics University of Edinburgh Edinburgh UK

ISBN: (纸本)9781665421874

Singing voice synthesis (SVS) is a task using the computer to generate songs with lyrics. So far, researchers are focusing on tunning the pre-recorded sound pieces according to rigid rules. For example, in Vocaloid, one of the commercial SVS systems, there are 8 principal parameters modifiable by song creators. The system uses these parameters to synthesize sound pieces pre-recorded from professional voice actors. We notice a common difference between computer-generated songs and real singers' songs. This difference can be addressed to help the generated ones become more like the real-singer ones. In this paper, we propose SinGlow, as a solution to minimise this difference. SinGlow is one of the Normalizing Flow that directly uses the calculated Negative Log-Likelihood value to optimize the trainable parameters. This feature gives SinGlow the ability to perfectly encode inputs into feature vectors, which allows us to manipulate the feature space to minimize the difference we discussed before. To our best knowledge, we are the first to propose an application of Normalizing Flow in SVS fields. In our experiments, SinGlow shows the ability to make the input virtual-singer songs more human-like. The code of the SinGlow model is available at https://***/discover304/singlow.

关键词： Codes Computational modeling Focusing learning (artificial intelligence) computer architecture Data models Probability distribution

来源：评论

学校读者我要写书评

暂无评论

A drug information embedding method based on graph convolution neural network 22

A drug information embedding method based on graph convoluti...

引用

22nd IEEE international conference on E-Health Networking, application and Services, HEALTHCOM 2020

作者： Feng, Xiaoyi Peng, Shaoliang Li, Fei Xu, Ying Zeng, Xiangxiang Wei, Dong-Qing Liu, Yunhao College of Computer Science and Electronic Engineering Hunan University China Beijing Institute of Radiation Medicine Department of Biotechnology China Laboratory of Microbial Metabolism School of Life Sciences and Biotechnology Joint Laboratory of International Cooperation in Metabolic and Developmental Sciences Ministry of Education Shanghai Jiao Tong University China Peng Cheng Lab Shenzhen518000 China

ISBN: (纸本)9781728162676

New drug development is an extremely time-consuming and high-risk process. [1]It has been widely valued by the biomedical industry to fully explore the new uses of existing drugs and reorientate them. [2]How to find drug disease with potential therapeutic relationship from a large number of unproven relationship pairs is the research focus of drug reorientation. With the help of machine learning model, we can improve the enrichment degree of potential drug disease relationship pairs, and reduce the false positive rate of prediction. In the past few years, a series of graph based convolutional network models have been developed to calculate the information latent feature representation of nodes and links. Researchers at home and abroad have done a lot of research on network embedding technology based on biomedical data, and have achieved a series of important research results. Among them, the research methods used can be divided into two categories: one is the traditional machine learning algorithm based on artificial feature extraction, the other is the method based on deep learning. For example, kipf and welling [3]proposed a new graph convolution network (GCN) with parts of existing models, DeepDR [4] and DTINet [5] based on node characteristics and their connections, which can be used for node classification. Aiming at the problem of imbalance of drug information data samples, the invention provides a drug relocation method based on deep learning multi-source heterogeneous network. In order to avoid the limitations of traditional feature extraction methods, such as highly dependent on the experience and knowledge of medical staff, strong subjectivity, consuming a lot of time and energy to complete, and extracting high-quality features with distinguishing features often exists In this paper, with the help of graph convolution encoder model and variational auto encoder neural network, we can automatically learn the characteristics of multi-source and heterogeneous

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

The application of machine learning in Chess Endgames Prediction 20

The Application of Machine Learning in Chess Endgames Predic...

引用

Proceedings of the 2020 2nd international conference on Big Data and Artificial Intelligence

作者： Hongyue Li Nanjing Foreign Languages School Nanjing Jiangsu Province China

ISBN: (纸本)9781450376457

The prediction of the minimal steps required to win in chess endgames has always been a difficult task. It is the advent of machine learning that gives the possibility to solve this problem in a systematic way, if a correct model in machine learning is chosen and developed. Existing methods include Quinlan's (1983) application of Iterative Dichotomiser 3 (ID3). However, this algorithm does not always generate the smallest decision tree and the precision of this model is quiet limited. In contrast, if we apply methods in machine learning, the precision of the prediction of the number of steps will boosted dramatically. Thus, we construct three widely used machine learning models, namely decision tree, random forest and adaboost, to predict this problem and we also compared their performance in the prediction of optimal depth-of-win for White. With the proposed model, we finally achieved 65% accuracy.

关键词： machine learning Random Forest Decision Tree Adaboost

来源：评论

学校读者我要写书评

暂无评论

application of Deep Convolution Neural Network in Breast Cancer Prediction using Digital Mammograms

Application of Deep Convolution Neural Network in Breast Can...

引用

international Informatics and Software Engineering conference (UBMYK)

作者： Rafsan Al Mamun Gazi Abu Rafin Adnan Alam Md. Al Imran Sefat BRAC University Dhaka Bangladesh

ISBN: (纸本)9781665407601

Cancer, a diagnosis so dreaded and scary, that its fear alone can strike even the strongest of souls. The disease is often thought of as untreatable and unbearably painful, with usually, no cure available. Among all the cancers, breast cancer is the second most deadliest, especially among women. What decides the patients' fate is the early diagnosis of the cancer, facilitating subsequent clinical management. Mammography plays a vital role in the screening of breast cancers as it can detect any breast masses or calcifications early. However, the extremely dense breast tissues pose difficulty in the detection of cancer mass, thus, encouraging the use of machine learning (ML) techniques and artificial neural networks (ANN) to assist radiologists in faster cancer diagnosis. This paper explores the MIAS database, containing 332 digital mammograms from women, which were augmented and preprocessed, and fed into a custom and different pre-trained convolutional neural network (CNN) models, with the aim of differentiating healthy tissues from cancerous ones with high accuracy. Although the pre-trained CNN models produced splendid results, the custom CNN model came out on top, achieving test accuracy, AUC, precision, recall and $\mathbf{F}_computer$ scores of 0.9362, 0.9407, 0.9200, 0.8025 and 0.8572 respectively while having minimal to no overfitting. The paper, along with proposing a new custom CNN model for better breast cancer classification using raw mammograms, focuses on the significance of computer-aided detection (CAD) models overall in the early diagnosis of breast cancer. While a diagnosis of breast cancer may still leave patients dreaded, we believe our research can be a symbol of hope for all.

关键词： Measurement Solid modeling Databases Computational modeling machine learning Breast cancer Mammography

来源：评论

学校读者我要写书评

暂无评论

Golden Ratio application in the Optimization of Cold-Formed Steel Sections 2nd

Golden Ratio Application in the Optimization of Cold-Formed ...

引用

2nd international conference on Sustainable Civil Engineering and Architecture, ICSCEA 2021

作者： Nguyen, Tran-Trung Nguyen, Phu-Cuong Nguyen, Hoang Thao Phuong Faculty of Architecture Van Lang University Ho Chi Minh City Viet Nam Advanced Structural Engineering Laboratory Department of Structural Engineering Faculty of Civil Engineering Ho Chi Minh City Open University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789811933028

The golden ratio is a ratio used popularly and is a standard to evaluate the beauty in architecture. This ratio appears in the fundamental rule and satisfies sustainable conditions to form and structural geometries in nature. This study will approve a valuable characteristic of the golden ratio when applied for optimizing the cold-formed steel sections’ geometries. The optimized problem is established by combining the parametric design software, such as Rhino grasshopper and 3D Karamba, with an applied Octopus. The post-optimized geometric sections archive symmetric forms and high strength when a typical C section combines each other based on the golden ratio. Besides, the proposed sections are evaluated with the experimental results using a finite element analysis to increase the proposed approach’s reliability. This study performs reliable and robust parametric design tools, especially with every analysis step in the optimized process. We will create collected data to build a predicted model about geometries and the strength curves of structures using machine learning Tools in later research. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Research on malicious Program Traffic Detection Technology based on Deep learning

Research on malicious Program Traffic Detection Technology b...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), international conference on IEEE international conference on

作者： Feng Li Jianye Zhang Bizhou He Bin Wang ShuTing Chen State Grid Xinjiang Electric Power Research Institute Urumqi China State Grid Xinjiang Electric Power Company Urumqi China State Grid Xinjiang Information and Communication Corporation Urumqi China

ISBN: (纸本)9781665428781

With the implementation of the strategy of “three types and two networks”, there are network security risks in every link of the power system, which is mainly reflected in the fact that the power information system has a large user base and large exposure, and at the same time stores a large amount of electricity customer data. bearing control business, once the system is breached, it will have a great impact on the society and economy. However, the network attack on power information system has the characteristics of “strong professionalism, deep latency, long persistence and great destructiveness”, so the security monitoring of power network and information system is faced with great challenges. Attackers generally use malicious programs to steal sensitive information, but with the progress of various intrusion detection technologies, malicious program anti-detection technology is also developing, which makes malicious program traffic very hidden and more difficult to be detected. Based on the shallow machine learning method, the ability to describe the characteristics of malicious programs is insufficient, and in the face of new malicious programs, such as inefficiency or failure, deep learning technology shows a strong learning ability in many application fields. this paper explores the research and application of malicious program traffic monitoring technology based on deep learning method. This paper studies the monitoring of abnormal traffic access behavior of malicious programs based on deep learning, and perceives abnormal traffic and security threats in real time.

关键词： Deep learning conferences Intrusion detection Network security Real-time systems Power grids Information technology

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104页 << < 95 96 97 98 99 100 101 102 103 104 > >>

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：