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

11,688 篇 会议
120 篇 期刊文献
18 册 图书
1 篇 学位论文

馆藏范围

11,827 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,237 篇 工学
- 6,595 篇 计算机科学与技术...
- 4,136 篇 软件工程
- 1,621 篇 控制科学与工程
- 1,414 篇 电气工程
- 1,377 篇 信息与通信工程
- 1,153 篇 生物工程
- 623 篇 机械工程
- 538 篇 生物医学工程（可授...
- 439 篇 交通运输工程
- 397 篇 动力工程及工程热...
- 396 篇 电子科学与技术（可...
- 388 篇 光学工程
- 301 篇 安全科学与工程
- 240 篇 仪器科学与技术
- 233 篇 材料科学与工程（可...
- 228 篇 化学工程与技术
- 220 篇 石油与天然气工程
3,409 篇 理学
- 2,035 篇 数学
- 1,230 篇 生物学
- 585 篇 物理学
- 579 篇 统计学（可授理学、...
- 407 篇 系统科学
- 266 篇 化学
2,004 篇 管理学
- 1,424 篇 管理科学与工程(可...
- 684 篇 图书情报与档案管...
- 605 篇 工商管理
567 篇 医学
- 491 篇 临床医学
- 431 篇 基础医学(可授医学...
- 299 篇 药学(可授医学、理...
429 篇 教育学
- 424 篇 教育学
227 篇 法学
211 篇 经济学
182 篇 农学
16 篇 文学
15 篇 军事学
15 篇 艺术学
2 篇 哲学

主题

867 篇 deep learning
774 篇 machine learning
710 篇 optimization
406 篇 accuracy
323 篇 reinforcement le...
277 篇 feature extracti...
230 篇 support vector m...
223 篇 computational mo...
220 篇 predictive model...
214 篇 training
201 篇 real-time system...
182 篇 neural networks
177 篇 particle swarm o...
164 篇 genetic algorith...
158 篇 data mining
151 篇 internet of thin...
149 篇 learning systems
149 篇 artificial intel...
144 篇 data models
143 篇 machine learning...

机构

60 篇 chitkara univers...
15 篇 school of comput...
15 篇 beijing universi...
14 篇 national univers...
14 篇 the islamic univ...
12 篇 tianjin universi...
12 篇 uttaranchal inst...
12 篇 national univers...
12 篇 weifang engineer...
11 篇 college of techn...
11 篇 misr internation...
11 篇 pune
11 篇 beijing institut...
10 篇 bengaluru
10 篇 uttaranchal univ...
10 篇 school of comput...
10 篇 school of comput...
9 篇 phaethon centre ...
9 篇 maharishi school...
9 篇 school of electr...

作者

17 篇 hassanien aboul ...
16 篇 lima jose
12 篇 wang lei
12 篇 yang bo
12 篇 li bo
11 篇 pereira ana i.
11 篇 wang wei
10 篇 malik bader alaz...
10 篇 liu yan
10 篇 chen xin
9 篇 li yan
8 篇 li xin
8 篇 li yang
8 篇 wang jing
8 篇 li li
8 篇 zhang chao
8 篇 liu yang
8 篇 li hao
8 篇 li xiang
7 篇 nagaraj p.

语言

11,009 篇 英文
789 篇 其他
74 篇 中文
2 篇 西班牙文

检索条件"任意字段=3rd Conference on Learning and Intelligent Optimization"

共 11827 条记录，以下是4781-4790 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：

On Customer Data Deduplication - Research vs. Industrial Perspective:: Lessons Learned from a R&D Project in the Financial Sector 5th

On Customer Data Deduplication - Research vs. Industrial Per...

引用

5th Workshop on intelligent Data - From Data to Knowledge, DOING 2024, 3rd Workshop on Knowledge Graphs Analysis on a Large Scale, K-GALS 2024, 6th Workshop on Modern Approaches in Data Engineering and Information System Design, MADEISD 2024 and 3rd Workshop on Personalization and Recommender Systems, PERS 2024 held in conjunction with 28th European conference on Advances in Databases and Information Systems, ADBIS 2024

作者： Andrzejewski, Witold Bębel, Bartosz Boiński, Pawel Wrembel, Robert Poznan University of Technology Poznań Poland Interdisciplinary Centre for Artificial Intelligence and Cybersecurity Poznań Poland

ISBN: (纸本)9783031704208

In this tutorial we present the results of researching, designing, implementing, and deploying data deduplication pipelines for customer records in a big financial institution. The tutorial is based on our experience gained within a R&D project. In the project we developed two deduplication pipelines. The first one is based on statistical modeling, whereas the second one is based on machine learning. Both pipelines were extensively tested on a real data set including customer records. The pipeline based on statistical modeling has already been deployed in the production system of the financial institution and processes batches of over 20 million of customer records. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Big Data Analytics and Mining Methods, Applications and Trends

Big Data Analytics and Mining Methods, Applications and Tren...

引用

Cloud Computing, Big Data Applications and Software Engineering (CBASE), International conference on

作者： Jian Li Siyi Wang Jinxiao Wang Dexian Zeng Space Engineering University BeiJing China

ISBN: (数字)9798331506582

ISBN: (纸本)9798331506599

In the era of big data information, along with the continuous development and application of 5G, online teaching, machine learning and other high-tech, the amount of information and data in many fields, such as education, scientific research, medical care, communication, e-commerce and so on, is growing geometrically. How to analyse and research these massive data more intelligently and efficiently, and mine the data information with practical application value, is the current key issue in the field of big data technology. Therefore, we need to further study and explore more efficient and intelligent data analysis and mining methods and techniques in order to better use big data technology to support the development of various fields.

关键词： Distance learning Education Medical services Machine learning Big Data Market research Data models Data mining Electronic commerce Software engineering

来源：评论

学校读者我要写书评

暂无评论

Construction and Application of intelligent Sports CAI System Based on K-Means Clustering Algorithm 3

Construction and Application of Intelligent Sports CAI Syste...

引用

3rd International conference on Artificial Intelligence and Advanced Manufacture, AIAM 2021

作者： Wu, Cuiping Ye, Liaokun Wu, Han School of Physical Education Kunming University Yunnan Kunming City 650214 China WUHAN SPORTS UNIVERSITY Hubei Wuhan City 430079 China

ISBN: (纸本)9781450385046

Under the background of the rapid development of information technology, my country's sports industry is facing huge challenges. K-means clustering algorithm is a typical optimization method based on data characteristics and original sample data. Faced with the quantitative data of sports and the development of Internet technology, the design of intelligent sports teaching auxiliary system becomes more and more important. For this reason, this paper studies the intelligent sports CAI system based on k-means clustering algorithm, the purpose is to provide a way to assist sports teaching through system design. This article mainly uses the investigation method and the interview method to understand the students' opinions of the intelligent sports CAI system. And applied the data method to research and describe the K-means clustering algorithm, and analyze the existing problems of the computer-aided teaching system. The survey results show that 59.1% of people attach great importance to the teaching and learning of intelligent sports. © 2021 ACM.

关键词： Computer aided instruction

来源：评论

学校读者我要写书评

暂无评论

Detecting Criminal Activities From CCTV by using Object Detection and machine learning Algorithms

Detecting Criminal Activities From CCTV by using Object Dete...

引用

intelligent Technologies (CONIT), International conference on

作者： Surbhi Singla Raman Chadha CSE AIML University Institute of Engineering Chandigarh University Mohali India CSE University Institute of Engineering Chandigarh University Mohali India

Now, a day’s Crime in every country is increasing day by day. Generally, Every day we listen to the news of different crimes of different categories like rape, assault, Kidnapping ,Robbery ,ATM Theft, Murders etc happening in different states, cities , countries. Almost all the newspapers, TV channels’, social media are filled with the news of Criminal activities happening all around the Whole World. In earlier times there is no method to detect Crime. After That the CCTV cameras were used to detect Crimes. But Watching these Videos manually by humans for detecting crimes is a very time Consuming process especially in today’s world of Artificial Intelligence and Machine learning .So this crime detection in CCTV surveillance becomes an important area of research in the field of machine learning. So, there is a very urgent need of the intelligent system which will detect the crimes from the real time CCTV Feed and classify them and provides an alert system to the nearest police stations and ambulances etc. So, that system will help in reducing the crime rate in any country. This paper reviews all prior research in this area, including approaches for object recognition and finding priority frames, techniques and algorithms like Yolo used to detect crimes , various datasets used and algorithms used to analyze crime data and train the dataset .It covers the various recent trends in researches in this field and analyzing the challenges faced and various research gaps and this paper also discuss how we can overcome these gaps in research so as to develop a better intelligence surveillance system in ml field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learn to Bind and Grow Neural Structures 21

Learn to Bind and Grow Neural Structures

引用

3rd ACM India Joint International conference on Data Science and Management of Data (CODS-COMAD)

作者： Shaikh, Azhar Sinha, Nishant PES Univ Bengaluru Karnataka India OffNote Labs Bengaluru Karnataka India

ISBN: (纸本)9781450388177

Task-incremental learning involves the challenging problem of learning new tasks continually, without forgetting past knowledge. Many approaches address the problem by expanding the structure of a shared neural network as tasks arrive, but struggle to grow optimally, without losing past knowledge. We present a new framework, Learn to Bind and Grow, which learns a neural architecture for a new task incrementally, either by binding with layers of a similar task or by expanding layers which are more likely to conflict between tasks. Central to our approach is a novel, interpretable, parameterization of the shared, multi-task architecture space, which then enables computing globally optimal architectures using Bayesian optimization. Experiments on continual learning benchmarks show that our framework performs comparably with earlier expansion based approaches and is able to flexibly compute multiple optimal solutions with performance-size trade-offs.

关键词： neural networks continual learning dynamic network expansion

来源：评论

学校读者我要写书评

暂无评论

A compound convolutional neural network used to process small perturbation 3

A compound convolutional neural network used to process smal...

引用

2021 3rd International conference on Robotics, intelligent Control and Artificial Intelligence, ICRICA 2021

作者： Ni, W.H. Xu, Shu CHINA NANHU ACADEMY of ELECTRONICS and INFORMATION TECHNOLOGY Jiaxing China

Input samples formed by deliberately adding subtle interference to the data set may cause the model to give false outputs with high confidence. To solve this problem, this paper proposes a deep learning method. Different interference sources can be considered to be independent of each other. Therefore, different networks are trained based on densenet for different interference sources. Then, the data set added to the combined interference item is sent to each neural network, and the output of each network is used as the input of the neural network in the next stage. The next stage of the neural network is used for multi-objective classification based on the output of the neural network. The output of the neural network is disturbed by adding different features to the input data. Because the depth network of each type of interference is independent, when introducing a new interference term, only the depth network and full connection layer of the new interference term need to be trained, rather than the whole network, which greatly simplifies the training process when introducing a new interference source. © Published under licence by IOP Publishing Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Natural Language Query to SQL conversion using Machine learning Approach 3

Natural Language Query to SQL conversion using Machine Learn...

引用

3rd International conference on Sustainable Technologies for Industry 4.0 (STI)

作者： Arefin, Minhazul Hossen, Kazi Mojammel Uddin, Mohammed Nasir Jagannath Univ Dept Comp Sci & Engn Dhaka Bangladesh

ISBN: (纸本)9781665400091

Natural Language Processing is a computer science and artificial intelligence topic concerned with computer-human language interactions and how computers are designed for processing and exploring a variety of natural language data, in particular. The Structured Query Language for non-expert users is usually challenging database storage, they may not know the database structure. For database applications to improve the interaction between database and user, a new intelligent interface is therefore necessary. The concept of utilizing a natural language instead of a structured query language has led to the creation of the natural language interface to database systems as a new form of the processing procedure. This research aims to build a query generating process using an algorithm for machine learning to represent information according to the user's demands for answering the query and obtaining information. For the conversion of Natural Language Query into Structured Query, we utilized a lowercase conversion, removing escaped words, tokenization, PoS tagging, word similarity, Jaro-Winkler matching algorithm, and the method Naive Bayes.

关键词： Natural Language Interfaces with Database Natural Language Processing Machine learning Structured Query language Machine Translation

来源：评论

学校读者我要写书评

暂无评论

Material Consumption Prediction of Modern intelligent Supply Chain for Electric Grid Based on Deep learning

Material Consumption Prediction of Modern Intelligent Supply...

引用

International conference on Electronics and Information Technology (EIT)

作者： Shaopeng He Yuanjie Rong Zhiwei Song Wenli Zhu Chenpeng Li Meichen Yan Jiandang Yang Yanqing Fu State Grid Materials Co. Ltd. Beijing China Zhejiang University Hangzhou China Binjiang Institute of Zhejiang University Hangzhou China

ISBN: (数字)9798350369151

ISBN: (纸本)9798350369168

Predicting material consumption in modern intelligent supply chains for electric grids is crucial for optimizing inventory management and ensuring efficient operations. Traditional forecasting methods often struggle with the complexity and non-linearity of supply chain dynamics, especially in the context of rapidly evolving technologies and fluctuating demand patterns. This paper proposes a novel approach utilizing deep learning techniques to forecast material consumption accurately. First, the material programme management framework is analysed. Then, a networked warehousing system is constructed to storage and dispatch materials. In addition, an efficient material inventory management approach is proposed. Next, based on long short-term memory (LSTM) neural network in deep learning technology, a material consumption prediction model is built to accurately predict material consumption, which helps for the modern intelligent supply chain construction of electric grid businesses. Finally, some practical examples exhibit that the established material consumption prediction model can accurately predict material consumption. This research underscore the potential of deep learning in revolutionizing supply chain management for electric grids, paving the way for more resilient and sustainable energy infrastructures.

关键词： Deep learning Supply chain management Program management Supply chains Warehousing Neural networks Predictive models Inventory management Long short term memory Business

来源：评论

学校读者我要写书评

暂无评论

Understanding the Determinants of Student Burnout in Blended learning Environments

Understanding the Determinants of Student Burnout in Blended...

引用

Educational Technology (ICET), IEEE International conference on

作者： Yaxin Tu Changqin Huang Xuemei Wu Tao He Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Jinhua China School of Information Technology in Education South China Normal University Guangzhou China

The negative phenomenon of student burnout, which may result in a considerably poor experience and low achievement, has drawn much attention in education and psychology. However, knowledge is scarce regarding the determinations of student burnout in blended learning environments. Accordingly, this study developed and validated a predictive model that explains the role of social support and self-regulated learning in predicting student burnout in blended learning environments. A comparative method using the Partial Least Squares Structural Equation Modelling (PLS-SEM) and machine learning algorithms was employed to validate the proposed model based on data gathered from 303 students. The PLS results demonstrated the negative role of perceived social support and self-regulated learning in alleviating burnout and the fully mediating role of self-regulated learning in the relationship between offline received social support and student burnout. Further, the applied algorithms predicted student burnout with an accuracy of more than 70% in most cases. The evidence from these findings provides the instructors and developers of courses in higher educational institutions with best practices to prevent and alleviate student burnout in blended learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2D/3D US-TO-MRI RIGID REGISTRATION BY DEEP learning 21

2D/3D US-TO-MRI RIGID REGISTRATION BY DEEP LEARNING

引用

3rd International conference on intelligent Medicine and Image Processing (IMIP)

作者： Han, JiaXin Fu, TianYu Fan, JingFan Deng, QiaoLing Yang, Jian Beijing Inst Technol Sch Opt & Photon Res Ctr Mixed Real & Adv Display Lab Beijing Engn Beijing 100081 Peoples R China

ISBN: (纸本)9781450390057

2D ultrasound (US) images to 3D magnetic resonance (MR) image registration is a crucial module in US-guided surgical navigation. US images need to be aligned with a preoperative image to provide good anatomy information guidance during interventions. However, the difference between the modality of US and MR makes the task challenging. To address this problem, we propose a learning-based rigid registration method between 2D US and 3D MR. The geodesic distance on the special Euclidean group SE(3) equipped with a left-invariant Riemannian metric is used as the loss function of a regression network. The registration result is optimized from the registration network by maximizing the similarity metric defined by a local structure orientation descriptor (LSOD). We achieve the angle and distance errors of 3.83 +/- 0.39 degrees and 0.017 +/- 0.001 mm, outperforming the L2 norm loss function which results in 4.21 +/- 0.19 degrees angle error and 0.039 +/- 0.001 mm distance error. Qualitative and quantitative evaluations confirm that the proposed method can achieve accurate 2DUS-3DMRI rigid registration.

关键词： 2DUS-3DMRI Rigid registration Deep learning

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 << < 475 476 477 478 479 480 481 482 483 484 > >>

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：