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

40,643 篇 会议
107 篇 期刊文献
97 册 图书

馆藏范围

40,847 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

23,198 篇 工学
- 19,975 篇 计算机科学与技术...
- 18,068 篇 软件工程
- 7,920 篇 信息与通信工程
- 7,818 篇 生物工程
- 4,908 篇 控制科学与工程
- 3,903 篇 生物医学工程（可授...
- 3,010 篇 电气工程
- 2,745 篇 光学工程
- 1,950 篇 网络空间安全
- 1,864 篇 电子科学与技术（可...
- 1,652 篇 安全科学与工程
- 1,454 篇 机械工程
- 1,447 篇 交通运输工程
- 1,366 篇 动力工程及工程热...
- 1,260 篇 化学工程与技术
14,311 篇 理学
- 8,021 篇 生物学
- 6,113 篇 数学
- 3,105 篇 物理学
- 2,815 篇 统计学（可授理学、...
- 1,494 篇 化学
- 1,468 篇 系统科学
7,539 篇 管理学
- 4,233 篇 图书情报与档案管...
- 3,727 篇 管理科学与工程(可...
- 2,029 篇 工商管理
3,626 篇 医学
- 3,142 篇 临床医学
- 3,075 篇 基础医学(可授医学...
- 2,389 篇 药学(可授医学、理...
- 1,394 篇 公共卫生与预防医...
1,569 篇 法学
- 1,396 篇 社会学
1,324 篇 教育学
- 1,320 篇 教育学
1,127 篇 农学
808 篇 经济学
284 篇 文学
53 篇 军事学
2 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

2,395 篇 deep learning
1,941 篇 machine learning
826 篇 support vector m...
650 篇 convolutional ne...
567 篇 training
547 篇 feature extracti...
537 篇 forecasting
481 篇 computational mo...
467 篇 reinforcement le...
461 篇 machine learning...
458 篇 object detection
423 篇 computer vision
411 篇 neural networks
409 篇 internet of thin...
394 篇 predictive model...
355 篇 covid-19
334 篇 long short-term ...
311 篇 transfer learnin...
261 篇 image segmentati...
258 篇 convolution

机构

469 篇 chitkara univers...
135 篇 computer science...
126 篇 school of comput...
88 篇 karnataka bangal...
85 篇 college of compu...
83 篇 centre of interd...
67 篇 school of comput...
61 篇 school of comput...
59 篇 graphic era deem...
58 篇 school of comput...
53 篇 department of co...
50 篇 medical technica...
49 篇 computer science...
48 篇 maharishi school...
47 篇 school of comput...
46 篇 department of co...
43 篇 computer science...
43 篇 the islamic univ...
42 篇 department of co...
40 篇 maharishi school...

作者

61 篇 shiva mehta
49 篇 sharma vikrant
40 篇 anjali t.
37 篇 vinay kukreja
34 篇 rakesh kumar
30 篇 deepak gerard
29 篇 sharma neha
27 篇 gill kanwarparta...
25 篇 vishal jain
25 篇 sheshang degadwa...
25 篇 li li
25 篇 nagaraj p.
24 篇 rishabh sharma
24 篇 kukreja vinay
22 篇 pareek piyush ku...
22 篇 shanmugasundaram...
21 篇 yu wang
21 篇 dhairya vyas
20 篇 kumar manish
20 篇 p nagaraj

语言

20,951 篇 英文
19,890 篇 其他
1,038 篇 中文
1 篇 德文

检索条件"任意字段=2023 International Conference on Computer Engineering and Distance Learning, CEDL 2023"

共 40847 条记录，以下是4251-4260 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：

Web-based Cattle Disease Detection 14

Web-based Cattle Disease Detection

引用

14th international conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Deshmukh, Vijayalaxmi Dhodamal, Aishwarya Ainapure, Rutuja Yelur, Dipali More, Harshal Department of Computer Science and Engineering RIT Maharashtra Sangli India

Cattle animals are vulnerable to many diseases, which can reduce their productivity and if not detected can lead to death of the cattle. This thesis provides a methodology that how the machine learning can detect cattle diseases that may provide affordable solution to the farmers with scarce in medical facilities to the animals. However, the system provides a user interface on a website in the form of web application and use Machine learning Logistic Regression to classify the data according to animals, diseased part, symptoms and use image processing to identify the related disease and provide immediate cure for the disease and the option to contact veterinarians near them accordingly. © Grenze Scientific Society, 2023.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Exploring Artificial Neural Networks in Virtual Reality: A Unity and Leap Motion-Based Visualization of ONNX Models 9

Exploring Artificial Neural Networks in Virtual Reality: A U...

引用

9th international conference on Virtual Reality, ICVR 2023

作者： Naqvi, Manzood Sujith, P.P. Naidu, Sohan Thomas, Kevin Ananthanagu, U. Pes University Computer Science Engineering Bangalore India

ISBN: (纸本)9798350345810

There is a rapidly increasing need for learning resources in the field of Artificial Intelligence aimed at newcomers. To this end, we have attempted to make an intuitive visualization of Artificial Neural Networks in Virtual Reality, while trying to make it as general and extensible as possible to allow for future work to build upon it to create a series of highly intuitive and interactive learning resources. Our implementation results in a framework built using careful design considerations that we think results in a solid building block for work that aims to interactively educate individuals in fields such as Artificial Intelligence and other such algorithms. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks 23

Hybrid of DiffStride and Spectral Pooling in Convolutional N...

引用

8th international conference on Sustainable Information engineering and Technology, SIET 2023

作者： Rafif, Sulthan Azhar, Mohammad Faris Wahyu Pratama, Mochamad Arfan Ravy Ibad, Ahmad Mustafidul Yudistira, Novanto Muflikhah, Lailil Faculty of Computer Science University of Brawijaya Malang East Java Indonesia

ISBN: (纸本)9798400708503

Stride determines the distance between adjacent filter positions as the filter moves across the input. A fixed stride causes important information contained in the image can not be captured, so that important information is not classified. Therefore, in previous research, the DiffStride Method was applied, namely the Strided Convolution Method with which it can learn its own stride value. Severe Quantization and a constraining lower bound on preserved information are arises with Max Pooling Downsampling Method. Spectral Pooling reduce the constraint lower bound on preserved information by cutting off the representation in the frequency domain. In this research a CNN Model is proposed with the Downsampling Learnable Stride Technique performed by Backpropagation combined with the Spectral Pooling Technique. Diffstride and Spectral Pooling techniques are expected to maintain most of the information contained in the image. In this study, we compare the Hybrid Method, which is a combined implementation of Spectral Pooling and DiffStride against the Baseline Method, which is the DiffStride implementation on ResNet 18. The accuracy result of the DiffStride combination with Spectral Pooling improves over DiffStride which is baseline method by 0.0094. This shows that the Hybrid Method can maintain most of the information by cutting of the representation in the frequency domain and determine the stride of the learning result through Backpropagation. © 2023 ACM.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Analyzing Student Perspectives on learning Experience Using Latent Semantic Indexing Algorithm 6

Analyzing Student Perspectives on Learning Experience Using ...

引用

6th international conference on computer and Informatics engineering, IC2IE 2023

作者： Kurniawan, Rahmad Daqiqil Id, Ibnu Indra, Zul Universitas Riau Faculty of Mathematics and Natural Sciences Department of Computer Science Pekanbaru Indonesia

ISBN: (纸本)9798350345162

The lecturer's evaluation by a student (EDOM) application is valuable for collecting anonymous feedback from students about their respective lecturers at the end of each semester. This feedback plays a crucial role in assessing teaching quality, identifying areas for enhancement, and promoting a constructive learning environment. This study addressed the challenge of effectively extracting and analyzing meaningful topics from a substantial dataset of 31, 600 student feedback records during the odd semester of the 2022/2023 academic year. Therefore, we proposed the adoption of the Latent Semantic Indexing (LSI) algorithm. This study also provides an in-depth description of the evaluation technique employed for assessing the coherence of the modeling results using the coherence score. Through experimental testing, we obtained notable coherence scores for each topic model. The optimal combination of parameters, a = 5 and ß= 20, resulted in the highest coherence score of 0.429, indicating the most proficient model for capturing latent structures within the data. The evaluation technique enabled quantifying the topic model's interpretability and consistency, significantly bolstering the credibility of the findings. The insights derived from the LSI analysis empower educational institutions to discern areas necessitating improvement, tailor pedagogical approaches, and cultivate a more effective and enriching learning environment for students. © 2023 IEEE.

关键词： EDOM Latent Semantic Indexing learning experience student perspectives analysis

来源：评论

学校读者我要写书评

暂无评论

Dormant Neural Trojans 22

Dormant Neural Trojans

引用

22nd IEEE international conference on Machine learning and Applications, ICMLA 2023

作者： Fu, Feisi Kiourti, Panagiota Li, Wenchao Boston University Division of Systems Engineering BostonMA02215 United States Boston University Department of Electrical and Computer BostonMA02215 United States

ISBN: (纸本)9798350345346

We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that will remain dormant until it is activated. The activation is realized through a specific perturbation to the network's weight parameters only known to the attacker. Our analysis and the experimental results demonstrate that dormant Trojaned networks can effectively evade detection by state-of-the-art backdoor detection methods. © 2023 IEEE.

关键词： AI Security Backdoor attacks Deep Neural Networks

来源：评论

学校读者我要写书评

暂无评论

A federated learning algorithm based on hierarchical importance adaptive differential privacy 4

A federated learning algorithm based on hierarchical importa...

引用

4th international conference on Artificial Intelligence and computer engineering, ICAICE 2023

作者： Zhang, Pengyu Guo, Hanyang Fang, Chen Lu, Bingyao Information Engineering University Henan Zhengzhou450000 China Unit 96922 Henan Zhengzhou450000 China

ISBN: (纸本)9798400708831

Hierarchical Importance-based Private Federated learning is proposed to address the imbalanced privacy and data availability issue in classical differential privacy under the existing framework. By computing the importance vector of each feature using hierarchical importance propagation, the algorithm achieves precise model training by adding minimal noise to important features for accuracy and greater noise to less important features for privacy preservation. Experimental results on MNIST and CIFAR-10 datasets demonstrate significant improvement in model accuracy while adhering to privacy constraints, with performance comparable to the federal average algorithm. © 2023 ACM.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

A model parameter update strategy for enhanced asynchronous federated learning algorithm 3

A model parameter update strategy for enhanced asynchronous ...

引用

3rd IEEE international conference on computer Systems, ICCS 2023

作者： Sun, Yu Gao, Xin Shen, Ying Xie, Jianfei Yang, Jiandong Si, Nong Beijing University of Technology Faculty of Information Technology Beijing China North China Institute of Science & Technology Department of Internet of Things Engineering Hebei China Capinfo Technology Development Co. Ltd. Beijing China

ISBN: (纸本)9798350313666

Federated learning addresses the 'data islands' issue resulting from privacy concerns, enabling multiple users to train a model collaboratively without sharing their private datasets. However, in the model training process of federated learning, effectively coordinating the communication between participants and server is essential to improve the training efficiency. Traditional synchronous and asynchronous federated learning algorithms cannot meet the requirements of convergence efficiency and precision stability at the same time. In order to balance algorithm efficiency and model stability, this paper proposes a model parameter update strategy for an enhanced asynchronous federated learning algorithm (EAFL). This strategy requires the server to store the latest global model parameters, the last round of global model parameters, and the update part of both, and judge the issued model type according to the sensitivity difference of the client. The client executes different local update processes according to different model types to improve the training efficiency and maintain the stability of the training accuracy. The experimental results show that the EAFL algorithm achieves better training results on MNIST and CIFAR-10 data sets than the traditional federated learning parameter update algorithm. This improvement in training results can provide new thoughts to solve computer vision tasks such as object detection with scattered devices. © 2023 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of Gamification and Live Coding-Based Programming learning Platform to Foster learning Motivation of Vocational Students

Development of Gamification and Live Coding-Based Programmin...

引用

2023 international conference on Electrical and Information Technology, IEIT 2023

作者： Hidayat, Wahyu Nur Dwi Prasetyo, Wiji Zahiroh, Ayu Najmatus Maydi Syahri, Esa Pramudheva Afdloly, Mochammad Mu'iz Sari, Rahajeng Kartika Universitas Negeri Malang Department of Electrical Engineering and Informatics Malang Indonesia Smk Negeri 10 Malang Departement of Computer Network Engineering and Telecommunications Malang Indonesia

ISBN: (纸本)9798350327298

The current utilization of e-learning has not been able to increase participation and learning experience and motivate students to achieve educational goals. This research focuses on developing gamification-based learning media in Object-Oriented Programming (OOP) subjects to increase student learning motivation, determine the feasibility level of learning media, and determine the increase in student learning motivation. The method of the research is design thinking It is used to identify and better understand users in the use of applications, find problems faced by users, and can explore new ideas in the creation of appropriate application features in accordance with user needs. The results of expert media validation from the teacher, lecturer, and programmer amounted to 89.78% in the good category, for the material validation results of 91.33% in the very good category. Media use was implemented by 23 students of class XI RPL SMKN 12 Malang. The user trial results showed a percentage of 83.48% with good criteria. The student learning motivation test results showed a percentage of 81.26% with very high criteria. This shows the effect of gamification implementation in fostering student learning motivation. Gamification-based media has been tested for feasibility by media experts, material experts, and students. Therefore, the media is feasible and can be used as a learning support media in object-oriented programming subjects in Vocational High School. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

WDRKNN: Weighted distance Representation based Nearest Neighbor for Hyperspectral Remote Sensing Imagery Classification 14

WDRKNN: Weighted Distance Representation based Nearest Neigh...

引用

14th international conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Sharma, Monika Biswas, Mantosh National Institute of Technology Department of Computer Engineering Haryana Kurukshetra India University of Delhi Department of Computer Science Delhi India

ISBN: (纸本)9798350335095

Hyperspectral image (HSI) classification has enormous importance in the era of remote sensing and extensively sourced in a variety of promising applications. Most HSI classifications use the K-nearest neighbor (KNN) method due to its efficiency and simplicity. Although the KNN-based classification has lot of benefits, while this classification method has two big issues: firstly, the sensitivity of the k-neighborhoods affects KNN performance and secondly, moderate majority voting utilized there especially if the size of samples is quite small. To tackle these outliers, this paper suggests the weighted distance representation-based K nearest neighbor (WDRKNN) approach for improving the image classification results. In proposed WDRKNN, initially for each pattern class k nearest neighbors belongs to testing data samples are chosen and it has been employed to imply the testing data sample as their linear combinations. The localities related to the k-nearest neighbors for each pattern class represent as the weighted distance restrict their subsequent representations related constants. Decisively, the testing sample will be classified to a specific pattern class by the WDRKNN using the least representation-based distance between the classes. Experimental assessment on two HSIs: Pavia University and Indian Pines confirms that the suggested structure can significantly enhance HSI classification as compared to related state-of-the-art methodologies. © 2023 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Skin cancer classification using machine learning

Skin cancer classification using machine learning

引用

international conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Sujatha, E. Lavanya, T. Niveditha, C.M. Saranya, S. Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9781032669663

The skin diseases are manifest in variousforms, scarcity and low prevalence of efficient dermatologists, and the need for rapid and automated diagnosis. This aims to extend other works on dermatology by utilizing various methods of machine learning to distinguish various skin diseases and to improve the classification efficiencyby the use of taxonomy. We have trained our model using skin pictorial dataset, namely the ISIC archive and DermNet, and used the disease taxonomy, where they are available, to improve classification efficiency. At DermNet, we are establishing a new state-of-the-artmodel with a rate of 80% and an Area Under the Curve (AUC) of 98%. We have also prioritized the classification of all 622 unique sub-classes. In this data set and it also achieved 67% cure and 98% AUC. In the ISICarchives, we have classified the 7diseases with an average accuracy of 93% and an AUC of 99%. This study reveals that machine learning has very huge potential to demonstrate a different types of skin diseases with example. This plays a vital role in present diagnosis of skin diseases and help the clinicians in large-scale dermoscopic imaging. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Taxonomies

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 << < 422 423 424 425 426 427 428 429 430 431 > >>

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：