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

3,008 篇 会议
4 册 图书
4 篇 期刊文献

馆藏范围

3,016 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,283 篇 工学
- 2,033 篇 计算机科学与技术...
- 1,640 篇 软件工程
- 894 篇 信息与通信工程
- 655 篇 控制科学与工程
- 468 篇 网络空间安全
- 418 篇 生物工程
- 321 篇 电气工程
- 273 篇 生物医学工程（可授...
- 241 篇 电子科学与技术（可...
- 219 篇 仪器科学与技术
- 218 篇 石油与天然气工程
- 175 篇 动力工程及工程热...
- 146 篇 光学工程
- 119 篇 安全科学与工程
- 109 篇 机械工程
1,354 篇 理学
- 792 篇 数学
- 436 篇 生物学
- 278 篇 统计学（可授理学、...
- 241 篇 化学
- 192 篇 物理学
- 130 篇 系统科学
828 篇 管理学
- 526 篇 管理科学与工程(可...
- 435 篇 图书情报与档案管...
- 229 篇 工商管理
306 篇 医学
- 236 篇 临床医学
- 235 篇 基础医学(可授医学...
- 167 篇 药学(可授医学、理...
- 166 篇 公共卫生与预防医...
138 篇 法学
- 102 篇 社会学
87 篇 农学
- 86 篇 作物学
80 篇 经济学
80 篇 教育学
10 篇 军事学
2 篇 文学

主题

89 篇 deep learning
87 篇 machine learning
66 篇 internet of thin...
61 篇 blockchain
53 篇 big data
47 篇 support vector m...
46 篇 forecasting
45 篇 data mining
36 篇 students
34 篇 artificial intel...
34 篇 convolutional ne...
33 篇 feature extracti...
32 篇 long short-term ...
30 篇 decision trees
29 篇 sentiment analys...
26 篇 object detection
26 篇 training
25 篇 cybersecurity
24 篇 computer vision
24 篇 power electronic...

机构

58 篇 maharishi school...
57 篇 uttaranchal univ...
39 篇 vishwakarma inst...
36 篇 chitkara univers...
35 篇 vivekananda glob...
32 篇 national univers...
32 篇 the islamic univ...
29 篇 centre of interd...
27 篇 lovely professio...
24 篇 chitkara univers...
24 篇 vishwakarma inst...
24 篇 graphic era deem...
23 篇 sr university sc...
21 篇 school of comput...
20 篇 uttaranchal inst...
19 篇 graphic era hill...
18 篇 maharishi school...
16 篇 vishwakarma inst...
16 篇 college of pharm...
15 篇 ajloun national ...

作者

29 篇 chauhan rahul
17 篇 alazzam malik ba...
16 篇 joshi kapil
14 篇 dhabliya dharmes...
13 篇 gill kanwarparta...
13 篇 gehlot anita
13 篇 tiwari mohit
10 篇 kukreja vinay
10 篇 mondal dipannita
10 篇 vats satvik
10 篇 anand vatsala
9 篇 sharma neha
9 篇 gupta rupesh
9 篇 kumar bura vijay
8 篇 anjali t.
8 篇 kumar ritesh
8 篇 singh vaishali
8 篇 singh akhilendra...
8 篇 singh rajesh
8 篇 abdelminaam diaa...

语言

2,985 篇 英文
31 篇 其他
5 篇 中文

检索条件"任意字段=2023 IEEE 3rd International Conference on Data Science and Computer Application, ICDSCA 2023"

共 3016 条记录，以下是111-120 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 Surface Defect Detection in Submersible Pump Impellers Based on the Novel MXNet Deep Learning Model 3

Research on Surface Defect Detection in Submersible Pump Imp...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Li, Shiyang Li, Cheng School of Information Science and Engineering Yunnan University Kunming China

ISBN: (纸本)9798350341546

In industrial production, surface defects of submersible pump impellers often have a significant impact on equipment performance and lifespan. However, the current defect detection is mainly performed manually, which is time-consuming, inefficient, and prone to human errors. Furthermore, the existing mainstream automatic detection methods have limitations, such as limited accuracy, complexity of the model, and low generalization, which make them difficult to promote widely. Therefore, an automated technology that can improve the efficiency and accuracy of the detection process is urgently needed. This study aims to develop an automatic defect detection method based on a Convolutional Neural Network (CNN) called MXNet to ensure superior product quality and reduce manual labor. This model, derived from the Xception architecture, has been specifically tailored for the task with custom convolutional and fully connected layers for precise classification, data augmentation techniques and an incorporated attention module to highlight vital regions in input images, coupled with the utilization of binary cross-entropy loss and custom callback functions, and a strategy for dynamically adjusting the learning rate. To demonstrate the superiority of this model, we compared it with four mainstream defect detection models. Experimental results show that the average accuracy and average recall rate of MXNet on the validation set reached 99.23% and 98.95% respectively, outperforming the comparative models in all performance indicators with shorter runtime and fewer parameters. This suggests that MXNet can not only achieve high-accuracy defect detection but also has high practicality, and is expected to have broad application potential in future in-dustrial production practices. © 2023 ieee.

关键词： Casting classification Deep learning Defect detection Depthwise separable convolution

来源：评论

学校读者我要写书评

暂无评论

Exploration on Artificial Intelligence Technology in Power System State Estimation, Monitoring and Early Warning System 3

Exploration on Artificial Intelligence Technology in Power S...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Jie, Shi Yanxia, Zhang Xiong, Wang Xueying, Niu Haixi Power Supply Company of State Grid Qinghai Electric Power Company Qinghai816000 China Qinghai Green Energy Data Co. Ltd Qinghai810000 China

ISBN: (纸本)9798350341546

A modern dispatch center requires the ability to quickly, accurately, and comprehensively grasp the actual operation status of the power grid, predict and analyze the operating trend of the system, take corresponding measures to address problems that arise during operation, and provide decision-making for the next step of operation to ensure the safe and economic operation of the power grid. Therefore, developing new microcomputer monitoring and analysis methods has become an urgent task for the power grid dispatch department. The purpose of this article is to study the monitoring and warning system for power system state estimation based on artificial intelligence technology. In this design, the main technologies used include the Java platform, Document Object Model technology, Hibernate persistence technology, etc. On this basis, the data communication and analysis function module, state estimation and early warning monitoring module, and data viewing function were designed, and the entire monitoring system architecture was ultimately implemented. After the design was completed, the system testing was completed using black box as the main testing method. The test structure showed that the upgraded and optimized OPEN 3000 overcame the drawbacks of the original operation monitoring, and eliminated all functional bugs to 0, achieving its set concept. © 2023 ieee.

关键词： Artificial Intelligence Monitoring And Early Warning Power System State Estimation

来源：评论

学校读者我要写书评

暂无评论

Distributed Computing and data Processing Technology under the Power data Middleware Architecture 3

Distributed Computing and Data Processing Technology under t...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Zou, Yuelin Shen, Jia Yin, Rui Guo, Jiangtao Guo, Yi State Grid Xinjiang Electric Power Co. Ltd. Information and Communication Company Urumqi830002 China State Grid Xinjiang Electric Power Co. Ltd. Urumqi830002 China State Grid Info-Telecom Great Power Science and Technology Co. Ltd Fuzhou350001 China

ISBN: (纸本)9798350341546

With the establishment and development of integrated monitoring platforms and communication information platforms for intelligent substations, the data volume of the power system is showing explosive growth. However, existing data centers have poor processing capabilities for massive amounts of data, making it difficult to meet the multiple service quality requirements of users. How to effectively manage massive and complex data, fully utilize the value of data, improve service quality, reduce operational costs, and achieve rapid response to users is an urgent problem to be solved. Therefore, based on the actual needs of power enterprises, this article proposed a cloud computing power data middleware architecture based on distributed technology, which effectively managed, cleaned, converted, and evaluated power data sources through cloud computing platforms. This article mainly analyzed the shortcomings of traditional power data processing platforms and the feasibility of cloud computing based power data platforms. Finally, through load balancing bias comparison and pressure testing experiments under different task numbers, it was proven that cloud computing systems outperformed traditional power data processing systems in terms of utility value, completion time, and load balancing. Moreover, in the pressure testing experiment, under the condition of 10 concurrent users and 673 system request transactions, 91.3% of the interface response time in the cloud computing system was within 50ms. Therefore, cloud computing systems have certain advantages in processing power data. © 2023 ieee.

关键词： Cloud Computing data Center System data Processing Distributed Computing Electricity data

来源：评论

学校读者我要写书评

暂无评论

Analysis and research of retail customer consumption behavior based on support vector machine 3

Analysis and research of retail customer consumption behavio...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Li, Xingyan Ye, Weile Zou, Miaojie Guo, Fusen Huang, Zhixing Monash University Faculty of Information Technology ClaytonVIC Australia New York University College of Arts & Science New York United States Monash University Malaysia School of Business Selangor Malaysia Deakin University School of Information Technology VIC Australia Monash University Monash Business School Caulfield EastVIC Australia

ISBN: (纸本)9798350341546

In recent years, with rapid economic development, customers' consumption levels have significantly increased and surpassed previous levels. This has placed enormous pressure on enterprise customer relationship management systems, especially for large-scale retail businesses. Faced with expanding data resources and massive volumes of static customer information and dynamic transactional data, traditional database technologies are no longer capable of meeting the analytical needs of modern requirements. Discovering the rules, relationships, and valuable insights hidden within vast amounts of data has become a focal point and challenge for businesses' future research. With the continuous improvement and introduction of data mining methods such as Support Vector Machines (SVM) and Decision Trees, they can provide certain assistance in this regard. This article introduces Support Vector Machines and applies them to the analysis and research of customer consumption behavior in the retail industry. Firstly, a Support Vector Machine-based model, known as the DCSS model, is proposed and constructed for analyzing customer consumption behavior. The model utilizes a cloud-like processing mapping mechanism and non-deterministic reasoning, combined with the probability distribution function of SVMDT, to apply an improved Sequential Minimal Optimization (SMO) algorithm for generating classification results on customer consumption data. Subsequently, through the analysis and research of instances, the SMO algorithm based on the DCSS model is compared with other algorithms. The results demonstrate that the efficiency and accuracy of the algorithm in this article are relatively high, making it suitable for application in customer classification scenarios in the retail industry. © 2023 ieee.

关键词： customer consumption behavior DCSS model retail businesses SMO SVM

来源：评论

学校读者我要写书评

暂无评论

application of Coleoptera Elytra for Protection of Winged Drones 3

Application of Coleoptera Elytra for Protection of Winged Dr...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Bao, Daniel Concordia International School Shanghai Shanghai China

ISBN: (纸本)9798350341546

Small UAVs are used in a multitude of contexts, including surveillance or transportation of goods. Fixed winged drones in certain environments risk damage to flight components, but no well-utilized solution has been created. Multirotor copters can use enveloping cages but a solution for winged drones is more complex. The purpose of this research is to determine the viability of using Coleoptera elytra as an inspiration for a protection mechanism. The general framework for conducting this research centered around fabricating numerous prototypes, improving on the shortcomings of the previous ones. Early prototypes centered more on individual mechanisms while later prototypes focused on integrating all components. Simulations and tests were conducted on each prototype to determine durability and flight characteristics. The elytra in most tests even with low impact-tolerance plastics showed effective protection capabilities. However, the unoptimized aerodynamic qualities of wing surfaces and the body and unoptimized weight prevented the drone from becoming airborne. This research shows promise in using beetle elytra as an inspiration for protection of winged drones. At a smaller scale, elytra are a viable option, but needs to be optimized more in terms of materials usage and shape and tested further with larger scale prototypes. © 2023 ieee.

关键词： Coleoptera Elytra drones UAV

来源：评论

学校读者我要写书评

暂无评论

Research on Game Analysis and Prediction Based on ARIMA Time Series Model 3

Research on Game Analysis and Prediction Based on ARIMA Time...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Pi, Tuo Liu, Chong Wu, Yuchen Li, Shiyuan Hu, Huiying Dalian Polytechnic University School of Mechanical Engineering and Automation Dalian China Hubei University of Art and Science Food Science Technology College•Chemical Engineering College Xiangyang China

ISBN: (纸本)9798350341546

With the improvement of people's living quality and technology level, video games have become the product and trend which formed by the gradual evolution of people's entertainment forms. The New York Time currently offers a popular puzzle called Wordle everyday, where each player gets 6 chances to guess a 5-letter word[1]. A scatter plot has been drawn about the number of reported results varies over time according to the data file, fitting the curve. Therefore this passage finds that the number of reported results had risen sharply over time first in a short time, then it declines slowly over time. Its influence has been declined. Then the ARIMA time series model[2] is used to predict the interval for the number of reported results on March 1, 2023, that is, [10409, 10446]. At the same time, the word attribute is defined, which includes the frequency of word in books, the repetition of letters in a word and the part of speech. For the frequency of word, the data from Goole Books Ngram Viewer[3] has been found, standardized method is considering the number of occurrences per million words as frequency of word. The passage establishes the Pearson model[4] to analyse the correlation between attributes of words and the percentage of scores reported that were played in Hard Mode. The three attributes of the word do affect the percentage of scores reported that were played in Hard Mode and the the frequency of word has the greatest influence. Then, The TOPSIS model[5] was used to classify the words according to their difficulty, which is divided three types:hard, moderate difficulty, easy. Categorize each word by giving it an overall score. The wore'EERIE'belongs to the hard, which conform the result studied before. Hence the accuracy of the model is high. The above can help game developers or decision makers make more accurate decisions, thus increasing the popularity of the game. © 2023 ieee.

关键词： ARMIMA Pearson TOPSIS

来源：评论

学校读者我要写书评

暂无评论

GDEMO-HAT: Knowledge-guided Medical Text Classification Using Heterogeneous Graph-based Dependency Modeling with Hierarchical Attention 3

GDEMO-HAT: Knowledge-guided Medical Text Classification Usin...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Zhou, Yunfan Chen, Hao Li, Ying Sun, Xuxue Zeng, Hao Qin, Aihong Ma, Tongqing Shen, Shanshan Zhejiang University Polytechnic Institute Hangzhou China Zhejiang University College of Computer Science Hangzhou China University of Zhejiang College of Media Engineering Communication Hangzhou China Zhejiang University Zhejiang Hospital Hangzhou China

ISBN: (纸本)9798350341546

The medical texts contain rich information about the health status of patients, including personal demographic details, examination items, diagnostic narratives, and corresponding outcomes. There is often an underlying dependency between a patient and multiple medical texts. Such dependency has a substantial influence on the accuracy and reliability of the patient's comprehensive diagnostic outcomes, thus necessitating the modeling of dependency. Most of the existing studies on medical text classification focused only on textual content and often overlooked the inherent dependency between the patient and medical texts, leading to the loss of relevant contextual information. To address the above problems, we propose an approach for medical text classification using heterogeneous Graph-based DEpendency MOdeling with Hierarchical ATtention (GDEMO-HAT), which accounts for patient-notes dependency and retains the contextual information. We model the dependencies between the patients and their medical texts via heterogeneous graphs. To facilitate medical text mining, we incorporate domain knowledge into the construction of a Patient-Notes-Physician (PNP) graph. Based on the constructed PNP graph, we introduce the hierarchical attention mechanism for classification that assigns different levels of importance to nodes based on distinct semantic contexts and thereby effectively captures the intricate interdependencies among these nodes. The representations of dependencies are integrated at the semantic level, thereby enabling a more comprehensive understanding of textual data. To demonstrate the effectiveness of the proposed approach, we conduct a classification task of the diagnosis of cardiovascular and cerebrovascular diseases based on medical text. The classification accuracy rate achieves 94%, which is significantly higher than the performances of the other compared models, such as Bert. © 2023 ieee.

关键词： dependency modeling heterogeneous graph hierarchical attention mechanism medical text classification physician knowledge

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Learning Motivation Classification: Fusion of LSTM and Neural Ordinary Differential Equations 3

A Novel Approach to Learning Motivation Classification: Fusi...

引用

2023 ieee 3rd international conference on data science and computer application, icdsca 2023

作者： Xiaoqin, Lai Siyun, Zhou Jiangao, Zuo Jianzhen, Li Yuan, Lei Caiyun, Jiang Guangxi Science & Technology Normal University Laibin545004 China The Institute of Education Sciences Yiyang413000 China Yiyang Open University English Department Yiyang413000 China Guangxi Suhang Firefighting Technology Co. Ltd. Nanning530000 China

ISBN: (纸本)9798350341546

With the rapid expansion of online education and continuous advancements in information technology, in-depth analysis and understanding of students' learning motivation have become increasingly critical. Students' learning motivation may affect their participation and achievements, making accurate identification and classification of learning motivation significant. This study proposes an advanced integrated model that combines Long Short-Term Memory networks (LSTM) with Neural Ordinary Differential Equations (Neural ODEs) for the classification and analysis of learning motivation. The LSTM component focuses on capturing long-term dependencies in time series data, while the Neural ODEs part is responsible for modeling continuous dynamic processes. We delve into the mathematical properties of the model and provide comprehensive theoretical analysis through theorems, reasoning, and inference. Moreover, we designed a series of rigorous experiments using real online education datasets from the Tianchi platform for validation. The experimental results show that the integrated model significantly outperforms standalone LSTM, Neural ODEs, and the baseline Random Forest model on multiple performance metrics such as accuracy, recall, and F1 score. We also deeply analyze the contribution of different model components and discuss various implementation details and hyperparameter selections. The main findings and methods of this study not only offer new perspectives and tools for analyzing learning motivation in the field of online education but also provide valuable insights for other time series and continuous data classification tasks. © 2023 ieee.

关键词： Integrated Model Learning Motivation Classification Long Short-Term Memory networks Neural Ordinary Differential Equations Online Education Performance Evaluation

来源：评论

学校读者我要写书评

暂无评论

application of computer science and Technology Intelligence Based on Improved Decision Tree Algorithm 3

Application of Computer Science and Technology Intelligence ...

引用

3rd ieee international conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Bai, Songlin School of Computer and Information Hohai University Nanjing China

ISBN: (纸本)9798350317022

data mining is the process of discovering large data sets and revealing hidden laws. This paper aims to study the intelligent application analysis of computer science and technology based on the improved decision tree algorithm. Taking the improvement of the ID3 algorithm as the research goal, on the basis of analyzing the tasks of data mining, decision tree algorithm and the application development of computer science and technology, it proposes improved scheme of ID3 algorithm is presented and realized. Finally, this paper uses the ID3 algorithm and the improved ID3 algorithm to conduct a decision tree construction experiment. The experimental results show that compared with the ID3 algorithm, the improved algorithm reduces a lot of training logarithms, and therefore shortens the construction of the same training data. The decision tree is time-consuming and greatly improves the computing performance. © 2023 ieee.

关键词： computer science and Technology Decision Tree Algorithm ID3 Algorithm Intelligent application

来源：评论

学校读者我要写书评

暂无评论

Automated Construction and application of Operations and Maintenance Knowledge Graph 3

Automated Construction and Application of Operations and Mai...

引用

3rd international conference on computer science and Blockchain, CCSB 2023

作者： Zheng, Yongkun Zhao, Yibing Luo, Haoran Wei, Dengrong Liu, Chun Fu, Huazheng Chen, Kang Chen, Chong Zhao, Shuo China Telecom Research Institute Guangdong Guangzhou China

ISBN: (纸本)9798350359077

This paper presents a novel method for automatically constructing an operations and maintenance knowledge graph for systems. By combining the application of integrated APM Agent and predefined Prometheus labels, entities and their relationships are extracted from multiple data sources and the knowledge is integrated and iteratively updated. The method was applied to a real IT system, and its effectiveness was evaluated. The results show that this method can rapidly and accurately build an IT operations and maintenance knowledge graph, thereby improving the efficiency of IT operations management. © 2023 ieee.

关键词： Knowledge graph

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302页 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：