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

20,098 篇 会议
103 篇 期刊文献
49 册 图书

馆藏范围

20,250 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

14,204 篇 工学
- 11,476 篇 计算机科学与技术...
- 8,852 篇 软件工程
- 3,230 篇 信息与通信工程
- 2,497 篇 生物工程
- 2,262 篇 控制科学与工程
- 1,797 篇 电气工程
- 1,487 篇 生物医学工程（可授...
- 1,045 篇 机械工程
- 1,028 篇 光学工程
- 1,027 篇 电子科学与技术（可...
- 797 篇 安全科学与工程
- 778 篇 动力工程及工程热...
- 761 篇 交通运输工程
- 681 篇 仪器科学与技术
- 660 篇 化学工程与技术
- 484 篇 材料科学与工程（可...
6,786 篇 理学
- 3,489 篇 数学
- 2,659 篇 生物学
- 1,498 篇 统计学（可授理学、...
- 1,366 篇 物理学
- 844 篇 系统科学
- 738 篇 化学
4,237 篇 管理学
- 2,539 篇 管理科学与工程(可...
- 2,023 篇 图书情报与档案管...
- 1,281 篇 工商管理
1,434 篇 医学
- 1,287 篇 临床医学
- 1,240 篇 基础医学(可授医学...
- 764 篇 药学(可授医学、理...
- 631 篇 公共卫生与预防医...
693 篇 教育学
- 667 篇 教育学
560 篇 法学
488 篇 农学
450 篇 经济学
43 篇 军事学
27 篇 文学
8 篇 艺术学
1 篇 哲学

主题

1,326 篇 deep learning
1,122 篇 machine learning
832 篇 accuracy
558 篇 data mining
540 篇 support vector m...
526 篇 feature extracti...
430 篇 training
410 篇 data models
406 篇 convolutional ne...
398 篇 predictive model...
379 篇 internet of thin...
363 篇 real-time system...
328 篇 computational mo...
324 篇 neural networks
314 篇 big data
233 篇 reinforcement le...
200 篇 forecasting
180 篇 object detection
175 篇 machine learning...
170 篇 artificial intel...

机构

227 篇 chitkara univers...
64 篇 centre of interd...
54 篇 maharishi school...
43 篇 maharishi school...
34 篇 college of techn...
31 篇 pune
28 篇 school of comput...
28 篇 chitkara univers...
28 篇 the islamic univ...
28 篇 school of comput...
26 篇 karnataka bangal...
24 篇 computer science...
24 篇 computer science...
24 篇 uttaranchal inst...
23 篇 department of ar...
22 篇 graphic era deem...
22 篇 school of inform...
22 篇 department of in...
22 篇 national univers...
20 篇 department of co...

作者

23 篇 kukreja vinay
22 篇 gill kanwarparta...
21 篇 wang lei
20 篇 shiva mehta
19 篇 liu yang
18 篇 wang jing
16 篇 singh jagendra
15 篇 zhang tao
15 篇 malik bader alaz...
15 篇 joshi kapil
14 篇 yang yang
13 篇 zhang lei
13 篇 li yang
12 篇 meena belwal
12 篇 novais paulo
12 篇 li li
12 篇 liu ying
12 篇 zhang bo
11 篇 babu tina
11 篇 liu xin

语言

17,813 篇 英文
2,418 篇 其他
101 篇 中文
3 篇 土耳其文
2 篇 西班牙文
1 篇 俄文

检索条件"任意字段=3rd International Conference on Intelligent Data Engineering and Automated Learning"

共 20250 条记录，以下是4601-4610 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：

Deep learning for High-Speed Laryngeal Imaging Analysis 3

Deep Learning for High-Speed Laryngeal Imaging Analysis

引用

3rd IEEE international conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023

作者： Naghibolhosseini, Maryam Yousef, Ahmed M Zayernouri, Mohsen Zacharias, Stephanie Rc Deliyski, Dimitar D Michigan State University Department of Communicative Sciences and Disorders East LansingMI United States Michigan State University Department of Mechanical Engineering Statistics and Probability East LansingMI United States Head and Neck Regenerative Medicine Program Mayo Clinic Scottsdale Department of Otolaryngology-Head and Neck Surgery PhoenixAZ United States

ISBN: (纸本)9798350338263

High-speed imaging of the larynx provides a valuable means for studying vocal folds function and vibratory behaviors. Using laryngeal high-speed videoendoscopy (HSV) with a flexible nasolaryngoscope, one can record the detailed vibratory movements of vocal folds during connected speech. This high-speed imaging tool enables us to study the normal function of the vocal folds and how this function can be disrupted due to the presence of voice disorders. In this work, HSV data were utilized during connected speech from subjects with normophonic voices (no voice disorders) and a neurological voice disorder. The data were obtained using a high-speed camera, coupled with a flexible endoscope, at 4,000 frames per second. Deep learning was used for the analysis of the big HSV dataset to extract the vibratory behaviors of the vocal folds. This deep-learning-based tool achieved high levels of accuracy for analysis of challenging HSV data in connected speech. This tool provides a computationally cost-effective and an accurate measurement approach that could help design more advanced voice assessment protocols in future. © 2023 IEEE.

关键词： High speed cameras

来源：评论

学校读者我要写书评

暂无评论

High Frequency Forecasting on Stock Market using Machine learning 3

High Frequency Forecasting on Stock Market using Machine Lea...

引用

3rd international conference for Emerging Technology, INCET 2022

作者： Khot, Amruta Bhat, Rashmi Urunkar, Abhijeet Mudegol, Nandinee Walchand College of Engineering Sangli India St. John College of Engineering and Management Palghar India

ISBN: (纸本)9781665494991

Intraday stock trading has become a popular trend in US, Europe, and Indian markets and forecasting these rapid market movements have become an important topic in finance. With the emergence of technology and computing power machine learning and neural network, methodologies are becoming a reality and efficient way to solve problems. The trend of intraday trading has made the researchers and developers explore neural networks approach to forecast the high frequency changing data. We focused on gathering minute to minute changing data of 80 stocks belonging to 8 different sectors from S&P 500 and developed a custom double layer neural network which efficiently captures the dependencies in the stock market and allows us to predict the returns of a specific stock at the end of next 5th minute time interval. © 2022 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Research on ecosystem change monitoring and intelligent analysis system based on remote sensing data 3

Research on ecosystem change monitoring and intelligent anal...

引用

3rd international conference on Environmental Remote Sensing and Geographic Information Technology, ERSGIT 2024

作者： Yu, Bo Faculty of Resources Environment and Chemistry Chuxiong Normal University Yunnan Chuxiong675000 China

ISBN: (纸本)9781510690219

Ecosystem monitoring is crucial for regional sustainable development. Taking Henan Province's Yanjin County as the study area, this research constructed an ecosystem evaluation index system including vegetation coverage, water quality, and land use based on Sentinel-2 satellite image data from April to September 2023. Through remote sensing feature extraction and change detection methods, the spatiotemporal changes of regional ecological elements were analyzed. The results showed that the highest NDVI value was 0.86, the water area increased by 12.3% during the flood season, and the construction land increased by 3.2 square kilometers. The overall monitoring accuracy reached 87.5%, providing a scientific basis for regional ecological environment management. © 2025 SPIE.

关键词： Abiotic

来源：评论

学校读者我要写书评

暂无评论

Research on autonomous intelligent inspection technology of substation based on image recognition and computer vision 3

Research on autonomous intelligent inspection technology of ...

引用

3rd international conference on Electronics, Electrical and Information engineering, ICEEIE 2023

作者： Fang, Mengran Li, Jingya Cai, Li Wang, Zheng State Grid Information and Communication Industry Group Co. Ltd. Beijing Branch Beijing China

ISBN: (纸本)9781510671423

Substation is the core hub of power grid transmission, which provides the necessary guarantee for the safe and stable operation of substation and even the whole power grid. There are many kinds of electrical equipment in substation, and the distribution is dense. Different equipment shows obvious differences in appearance and state. When inspecting these electrical equipment, we can not only use traditional manual inspection methods, but also rely on artificial intelligence technology and big data technology to build an intelligent inspection robot, and realize the recognition of image information through image recognition technology. In this article, the application of intelligent inspection robot in autonomous intelligent inspection of substation is studied, and the path planning model of inspection robot is constructed by combining image recognition and computer vision technology. The experimental results show that the path planning algorithm of inspection robot in this article has small error and excellent accuracy, which can reach more than 98% after many iterations. The algorithm realizes the stable, reliable and high-precision inspection operation of the substation inspection robot. © 2023 SPIE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Study on the construction of gene regulatory network based on nonhomogeneous dynamic bayesian network 3

Study on the construction of gene regulatory network based o...

引用

3rd international conference on Biomedical and intelligent Systems, IC-BIS 2024

作者： Shao, Mingyi Hu, Chunling Dou, Yan Zhu, Guanyu Hu, Ruijie College of Artificial Intelligence and Big Data Hefei University Hefei China Electronic Information Engineering Anhui University of Architecture Hefei China

ISBN: (纸本)9781510681279

In gene regulatory networks, due to the influence of paradigm, the number of parent nodes of a gene node is always smaller than the sum of the number of other gene nodes in the network, so there must exist some nodes that are not the parents of that node. In the Hidden Markov's Non-Chiral Dynamic Bayesian Network (HMM-DBN) model, the sampling strategy of the parent node set is to sample all the nodes randomly, and does not take into account the correlation between the nodes in the network, and the no-joints are sampled many times, which leads to poor accuracy and slows down the rate of convergence in the process of constructing the network. To address this problem, this paper proposes a Hidden Markov Non-homogeneous Dynamic Bayesian Network (MICHMM-DBN) model based on node screening. The model identifies other nodes that have high correlation with a particular node through the maximum information coefficient and treats these nodes as candidate parent nodes for that particular node. Following this, Markov chain Monte Carlo (MCMC) sampling is performed on these candidate parent nodes to determine the final set of parent nodes. This method effectively reduces the search space and eliminates redundant connections, thus improving the accuracy of network construction. In a series of experiments conducted on synthetic datasets as well as real biological network data, the new model demonstrates higher network construction accuracy compared to the original model. © 2024 SPIE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Improved high-resolution network for palmprint principal line extraction 3

Improved high-resolution network for palmprint principal lin...

引用

3rd international conference on Electronic Information engineering and data Processing, EIEDP 2024

作者： Jia, Wei Zhou, Xin School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9781510680531

Recently, there has been growing interest in deep learning-based semantic segmentation. We propose a high-resolution network UC-HRNet for palmprint principal line extraction. Compared with other popular deep learning semantic segmentation networks, the performance is stronger. Dense prediction tasks rely heavily on both high-resolution imagery and sophisticated semantic representations for optimal performance. Generally, low-resolution feature maps excel in conveying robust semantic representations, whereas high-resolution feature maps excel in capturing fine-grained details like edges but may lack in semantic richness. Current cutting-edge frameworks, like HRNet, preserves the parallelism between low- and high-resolution feature maps and iteratively exchanges information across different resolutions. The success of UNet is mainly due to its U-shaped structure as well as jump *** symmetric U-shaped structure allows for a more thorough fusion of front and back features, it turns out that skip connections are effective in recovering complex details of target objects. We propose a kind of U-shaped structure based on HRNet and add skip connections to make it able to segment the target more accurately. We utilize deep supervision to acquire hierarchical representations from fully aggregated feature maps. Compared to other popular semantic segmentation networks, UC-HRNet proves its effectiveness on three master libraries of semantically segmented palmprints created by ourselves. © 2024 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Designing Robust Deep learning Models for RealTime data Analysis in Machine learning 3

Designing Robust Deep Learning Models for RealTime Data Anal...

引用

3rd international conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Borade, Monali R. Gupta, Mukur Faiz, Ayaan Acharjya, Kalyan Rajesh, A. Nunciya, P.M. Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science Engineering Faculty of Engineering and Technology Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Master of Business Administration Chennai127 India

ISBN: (纸本)9798350319125

The developing call for real-time statistics analysis and selection-making has been a primary driver of improving deep studying models for the device getting to know. These models permit the evaluation of massive statistics sets, the generation of predictions from the statistics, and the speedy studying of new behaviors and patterns. Deep mastering fashions have been efficaciously used for various tasks, including natural language processing, computer imagination and prescient, and reinforcement studying. However, because of their complexity and a massive variety of parameters, they can be unreliable and volatile when uncovered to real-global records. This paper outlines strategies and techniques to lay out deep mastering fashions that can be robust to actual-world records. We also provide high-quality practices for deploying and retaining deep learning models in manufacturing packages. Those strategies include regularization techniques, model architectures, facts pre-processing techniques, and model validation and monitoring techniques. We additionally speak of the numerous strategies for assessing and improving the reliability of deep getting-to-know fashions. Subsequently, we provide a case study of a product that uses deep studying fashions to stumble on and classify objects in near-actual time in a manufacturing place. © 2023 IEEE.

关键词： improving maintaining production regularization techniques

来源：评论

学校读者我要写书评

暂无评论

Research on feature surface thickness prediction based on transformer deep learning networks 3

Research on feature surface thickness prediction based on tr...

引用

3rd international conference on Electronic Information engineering and data Processing, EIEDP 2024

作者： Li, Xingzuo Su, Chengzhi Jiang, Feng Zhao, Guang Mei, Yufei School of Mechanical Engineering Changchun University of Science and Technology Changchun China School of artificial intelligence Changchun University of Science and Technology Changchun China School of Telecommunications Changchun University of Science and Technology Changchun China

ISBN: (纸本)9781510680531

Aiming at the problem of predicting the amount of material surface removal, this paper is based on the development and application of deep learning and the latest research results. It takes images of paint layers of different thicknesses attached to the surface of steel plates as the research object, and predicts and classifies the paint layer thickness based on the Transformer network algorithm. First, a steel plate paint layer thickness database is established, and after image preprocessing, it meets the requirements of Transformer network training and testing. Secondly, the Cross Former network (a multi-functional visual Transformer network model based on cross-scale attention) is selected to fine-tune the Cross Former network model. After network training and hyper-parameter optimization and adjustment, it can effectively predict the thickness of the paint layer. Again, by comparing the model training accuracy and test accuracy under different training hyperparameter settings, the optimal training hyperparameter values of the model are obtained, and the Cross Former network model under the optimal training hyperparameters is obtained. Finally, the polishing of the deep learning network prediction model is verified through experiments. The surface margin prediction theory was used and the paint layer thickness distribution map on the workpiece surface was drawn. The results showed that the real values in the experimental area were within the prediction range, which verified the effectiveness of the prediction model in actual application scenarios. © 2024 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Mental Confusion Prediction in E-learning Contexts with EEG and Machine learning 3rd

Mental Confusion Prediction in E-Learning Contexts with EE...

引用

3rd international conference on Novel and intelligent Digital Systems, NiDS 2023

作者： Trigka, Maria Dritsas, Elias Mylonas, Phivos Department of Informatics and Computer Engineering University of West Attica Athens Greece Department of Electrical and Computer Engineering University of Patras Patras Greece

ISBN: (纸本)9783031440960

In cognitive science, the term confusion is used to capture the decline in learners’ cognitive ability, which affects their ability to think, solve a problem, learn and understand. Unlike classroom education, in online e-learning contexts (e.g., in Massive Open Online Courses (MOOC)), confusion hinders the smooth evolution of the learning process from the learners’ side, as the educator can’t immediately interact with the students to restore cognitive equilibrium. This paper presents a Machine learning (ML) based approach by comparing several classifiers that were trained and tested exploiting Electroencephalogram (EEG) data (namely, band power, attention and mediation features) acquired by the MindSet device to efficiently distinguish "Confused" from "Not-Confused" subjects. In particular, J48 was the dominant model reaching an optimal performance with accuracy, precision and recall equal to 99.9% and an Area Under the Curve (AUC) of 100%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Research on the application of data mining technology in software engineering 3

Research on the application of data mining technology in sof...

引用

3rd international conference on Machine learning and Big data Analytics for IoT Security and Privacy, SPIoT2023

作者： Yitao, Lin School of Software Heilongjiang University Heilongjiang Province Harbin450000 China

The role of data mining in software engineering is obvious, but there is a lack of mining depth. In the past, engineering layout and function distribution problems in software development, and the framework construction was unreasonable. Therefore, this paper proposes a software system based on data mining technology. First, the software engineering project is divided, and the software engineering project design is carried out according to the interactive requirements to realize the preprocessing of software engineering. Then, according to the design criteria, the design collection of software engineering is formed, and the information system is analyzed in depth. MATLAB simulation shows that the design interactivity and accuracy of data mining are superior to traditional design methods under the condition that software engineering requirements are consistent. © 2023 Elsevier B.V.. All rights reserved.

关键词： data mining

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 << < 457 458 459 460 461 462 463 464 465 466 > >>

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：