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

1,324 篇 会议
27 册 图书
7 篇 期刊文献

馆藏范围

1,358 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

973 篇 工学
- 918 篇 计算机科学与技术...
- 634 篇 软件工程
- 236 篇 信息与通信工程
- 132 篇 控制科学与工程
- 101 篇 生物工程
- 97 篇 电气工程
- 64 篇 安全科学与工程
- 60 篇 动力工程及工程热...
- 58 篇 交通运输工程
- 58 篇 网络空间安全
- 47 篇 机械工程
- 47 篇 生物医学工程（可授...
- 42 篇 仪器科学与技术
- 29 篇 建筑学
- 28 篇 环境科学与工程（可...
354 篇 理学
- 183 篇 数学
- 113 篇 生物学
- 74 篇 统计学（可授理学、...
- 58 篇 化学
- 41 篇 物理学
- 31 篇 系统科学
346 篇 管理学
- 237 篇 管理科学与工程(可...
- 212 篇 图书情报与档案管...
- 121 篇 工商管理
62 篇 法学
- 52 篇 社会学
61 篇 医学
- 54 篇 临床医学
- 50 篇 基础医学(可授医学...
- 32 篇 药学(可授医学、理...
47 篇 经济学
- 47 篇 应用经济学
28 篇 教育学
- 28 篇 教育学
14 篇 农学
7 篇 文学
2 篇 军事学

主题

256 篇 big data
79 篇 artificial intel...
67 篇 cloud computing
63 篇 machine learning
50 篇 computational mo...
49 篇 deep learning
42 篇 internet of thin...
41 篇 data models
35 篇 training
27 篇 data mining
25 篇 neural networks
24 篇 smart cities
23 篇 predictive model...
23 篇 edge computing
21 篇 computational in...
21 篇 feature extracti...
19 篇 industries
18 篇 object detection
17 篇 social networkin...
16 篇 data privacy

机构

14 篇 ajou univ dept a...
13 篇 school of big da...
12 篇 renmin univ chin...
11 篇 beijing key lab ...
9 篇 college of compu...
7 篇 university of ch...
7 篇 beijing universi...
6 篇 school of comput...
6 篇 key laboratory o...
6 篇 school of comput...
6 篇 key laboratory o...
6 篇 shandong fundame...
5 篇 college of big d...
5 篇 national enginee...
5 篇 shiga university...
5 篇 ajou univ dept i...
5 篇 riken center for...
5 篇 gaoling school o...
5 篇 chongqing univ s...
5 篇 college of intel...

作者

13 篇 shin hyunjung
10 篇 liu yong
7 篇 geng xin
6 篇 zhou xiaokang
6 篇 dai fei
6 篇 mariano vladimir...
6 篇 li shaojie
6 篇 wang jun
5 篇 xu ning
5 篇 wang xiaofei
5 篇 li xiuhua
5 篇 yang yang
5 篇 su bing
5 篇 kim myungjun
5 篇 zhao wei
5 篇 qi jinli
5 篇 wu yanmin
5 篇 jin hai
5 篇 gao yanxia
5 篇 liu yiwen

语言

1,331 篇 英文
20 篇 其他
9 篇 中文
1 篇 西班牙文

检索条件"任意字段=International Conference on Big Data Intelligence and Computing, DataCom 2022"

共 1358 条记录，以下是281-290 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：

INTERPOLATION AND CONTEXT MAGNIFICATION FRAMEWORK FOR CLASSIFICATION OF SCENE IMAGES 16

INTERPOLATION AND CONTEXT MAGNIFICATION FRAMEWORK FOR CLASSI...

引用

16th international conference on Computer Graphics, Visualization, Computer Vision and Image Processing, CGVCVIP 2022, 8th international conference on Connected Smart Cities, CSC 2022, 7th international conference on big data Analytics, data Mining and Computational intelligence, bigDaCI 2022, and 11th international conference on Theory and Practice in Modern computing, TPMC 2022 - Held at the 16th Multi conference on Computer Science and Information Systems, MCCSIS 2022

作者： Balarabe, Anas Tukur Jordanov, Ivan School of Computing University of Portsmouth United Kingdom

ISBN: (纸本)9789898704429

Recently, there has been an upsurge in publicly available remote sensing image classification datasets. Standard CNNs and pre-trained architectures have been applied for scene classification tasks. However, transfer learning models accept specific image dimensions as the minimum required size for their respective image input layers. Depending on the size of the input image, the final feature map might not contain the discriminative information needed for accurately classifying the dataset categories. The proposed technique effectively enables and enhances a transfer learning model (Xception) to be applied to scene classification tasks. The model works on an adaptive framework that interpolates images and selects an appropriate dilation layer to enhance the quality of extracted features for improved classification. This approach is evaluated on the EuroSAT, a dataset with images of 64x64 pixels, UCM and AID datasets, respectively. We recorded 98.55%, 99.22%, and 96.15% accuracy for the EuroSAT, UCM, and AID datasets, respectively. Our model and the reported results have opened the potential of the Xception, which in our view, has not been given its fair share of attention, despite its efficient parameter utilisation. © MCCSIS *** rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Application of Quantum computing to Accurate Positioning in 6G Indoor Scenarios

Application of Quantum Computing to Accurate Positioning in ...

引用

IEEE international conference on Communications (ICC)

作者： Urgelles, Helen Picazo-Martinez, Pablo Monserrat, Jose F. Univ Politecn Valencia iTEAM Res Inst Valencia Spain

ISBN: (纸本)9781538683477

6G will lay its foundations on new paradigms and requirements. This new technology is expected to provide global coverage, exploring a huge spectral chunk (sub-6 GHz, mmWave, THz and optical frequency bands) to further increase data rates and connection density. In addition, 6G networks will enable a new range of smart applications with the aid of Artificial intelligence, big data technologies and the emerging paradigms of Quantum computing and Quantum Machine Learning. This paper focuses on these new paradigms and proposes an indoor location method based on the well known Euclidean Distance in its quantum version. Specifically, an example of this use case is shown, which is executed in one quantum computer from IBM Quantum *** paper analyses the obtained results while exploring new challenges and fields of application of the technology. Results show that the quantum approach is accurate enough to calculate Euclidean Distance between two vectors while outperforming classical computation if vector size is big enough.

关键词： Quantum computing 6G Wireless Communications Networks Indoor Localization

来源：评论

学校读者我要写书评

暂无评论

Research on Key Technologies of Network Intrusion Detection Based on Machine Learning

Research on Key Technologies of Network Intrusion Detection ...

引用

2022 international conference on Artificial intelligence, Information Processing and Cloud computing, AIIPCC 2022

作者： Ye, Chengqiong Sun, Mali Chen, Yang School of Big Data and Artificial Intelligence Anhui Xinhua University Hefei China School of Technology Anhui Xinhua University Hefei China

ISBN: (纸本)9781665462877

Network security is one of the most concerned issues today. Modern network attacks show a trend of technical complexity and diversification. Intrusion detection is an effective defense method to solve network security problems, but the accuracy and false alarm rate of traditional intrusion detection methods still have much room to improve, and it is difficult to accurately detect new types of attacks in real time, and the generalization is poor. This paper proposes the method of KNN and decision tree to establish machine learning model, and conducts simulation experiments on the classic dataset KDDCUP99. Combined with the experimental results of Bayes and BP neural network comparison models, it shows that KNN and decision tree have higher detection accuracy and reliability, and detection classification has more generalization and higher practicability. It also provides a reference for the application of KNN and decision tree machine learning methods in other big data detection classification. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Analysis of Stability big data Environment of Intelligent Financial data Abnormal Qo S System based on Wolf Pack Algorithm

Analysis of Stability Big Data Environment of Intelligent Fi...

引用

2022 international conference on Edge computing and Applications, ICECAA 2022

作者： Cui, Lijuan Shandong vocational animal science and veterinary college Shandong Weifang261061 China

ISBN: (数字)9781665482325

ISBN: (纸本)9781665482325

A new swarm intelligence algorithm, the Wolf Pack Algorithm has been proposed in this paper, and the convergence of the algorithm is proved based on the Markov chain theory. It reduces the risk of the algorithm falling into local optimum due to the excessively large penalty parameter. Inspired by the reproduction mode of wol ves, a big data environment analysis for the stability of the Qo S system for abnormal data is proposed based on the binary wolf pack algorithm. Moreover, the Convolutional Neural Network with 4 hidden layers is used to classify and evaluate the constructed time series financial data. data testing and analysis are performed using actual financial data. It is believed that the supervision system and relevant laws and regulations need to be improved first;secondly, the big data is used to collect personal credit records so as to establish a sound credit system as soon as possible;finally, through big data and computer technology, risk control methods are innovated to enhance the stability of Internet finance. © 2022 IEEE.

关键词： Computer control systems

来源：评论

学校读者我要写书评

暂无评论

Individual Identification of Communication Emitters in Open Electromagnetic Environments: A Multi-Feature Attention Method with OpenMax 8

Individual Identification of Communication Emitters in Open ...

引用

8th international conference on Smart Internet of Things

作者： Ya, Yixuan Wan, Liangtian Sun, Lu Zheng, Jianbo Wang, Xianpeng Dalian Univ Technol Sch Software Dalian 116620 Peoples R China Dalian Maritime Univ Inst Informat Sci Technol Dalian 116026 Peoples R China Shenzhen MSU BIT Univ Artificial Intelligence Res Inst Shenzhen Peoples R China Hainan Univ Sch Informat & Commun Engn Haikou 570228 Hainan Peoples R China

ISBN: (纸本)9798350366457;9798350366440

This paper proposes a Multi-Feature Attention Method based on OpenMax (MFAM-OM) for individual identification of communication emitters, aiming to address the challenges of open and dynamic electromagnetic environments in practical applications. Existing techniques mainly focus on closed-set classification, which can only identify known emitters and suffer significant performance degradation when encountering unknown classes, posing a threat to the security of communication systems. MFAM-OM consists of a data preprocessing and feature extraction fusion module, a channel and spatial attention module, and an open-set recognition module. By performing multi-level processing and feature fusion on input I/Q signals, combined with attention mechanisms to enhance feature selection and extraction, the method utilizes OpenMax to adjust the classifier's output probabilities. Experimental results on the ADS-B dataset show that MFAM-OM outperforms existing methods in recognizing both known and unknown classes, effectively reducing the risk of misidentification and improving system robustness and stability in complex environments. This demonstrates its broad potential for applications in both military and civilian fields.

关键词： Open Set Recognition Individual Emitter Recognition Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Hand Movement Classification from Spatio-Temporal Sensory data Based on Hybrid Random Forest Deep Learning 19

Hand Movement Classification from Spatio-Temporal Sensory Da...

引用

2022 IEEE SmartWorld, 19th IEEE international conference on Ubiquitous intelligence and computing, 2022 IEEE international conference on Autonomous and Trusted Vehicles conference, 22nd IEEE international conference on Scalable computing and Communications, 2022 IEEE international conference on Digital Twin, 8th IEEE international conference on Privacy computing and 2022 IEEE international conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Liang, Kun Zhao, Wei Qian, Heng Liu, Yanan Zeng, Zeng Shanghai University School of Microelectronics Shanghai China Shanghai Normal University School of Business Shanghai China University of Bristol Bristol Robotics Lab Bristol United Kingdom

ISBN: (纸本)9798350346558

The recognition of hand movements through electromyography signals (EMG) collected based on biosensors is a typical supervised pattern recognition problem. Moreover, effectively extracting spatial and temporal information from sensor temporal data has been a big challenge in machine learning and deep learning. When faced with high-dimensional small sample data, Machine Learning representation learning methods offer advantages over Deep Neural Networks. However, most machine learning approaches rely on feature extraction methods and do not have an advantage in the information extraction of temporal information. In contrast, temporally valid data can be better captured by neural networks. We propose a hybrid network of CNN-GRU and random forest based on existing methods. The CNN-GRU network will be used to fuse temporal and spatial information, and the random forest decision tree will guide the neural network in the lower layer of representation learning. This hybrid network captures the temporal and spatial information of the EMG signal very well. We obtained an accuracy of 99.72% for the Basic Hand movements data Set. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

PE-FedAvg: A Privacy-Enhanced Federated Learning for Distributed Android Malware Detection 21

PE-FedAvg: A Privacy-Enhanced Federated Learning for Distrib...

引用

21st IEEE international Symposium on Parallel and Distributed Processing with Applications, 13th IEEE international conference on big data and Cloud computing, 16th IEEE international conference on Social computing and Networking and 13th international conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Tang, Junwei Xu, Zilong Ye, Luyao Peng, Tao He, Ruhan Hu, Xinrong Tian, Wenlong Wuhan Textile University Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion China Wuhan Textile University School of Computer Science and Artificial Intelligence China University of South China School of Computer Science China Nanyang Technological University School of Physical and Mathematical Sciences Singapore

ISBN: (纸本)9798350329223

Android malware detection has become research hotspot in mobile security. When security service providers obtain feature information from target samples, they may involve user privacy information such as identity and behavioral habits, creating an urgent need for a distributed machine learning model to carry out malicious application detection with privacy protection. However, the information exchange between clients and servers in basic federated learning still poses risks of model data leakage, and the likelihood of inferring privacy information from the original feature data is high. Therefore, This paper propose a privacy-enhanced federated learning system called PE-FedAvg for distributed Android malware detection. Firstly, Gaussian noise is added to the feature data uploaded from the client to the server, satisfying differential privacy characteristics while retaining data distribution for privacy protection. Secondly, an improved homomorphic encryption algorithm based on modular repeated squaring is used to encrypt and transmit the gradient weight information exchanged between federated learning clients and servers, preventing model-targeted attacks. By conducting the experiments on the Drebin and Malgenome datasets, our design has demonstrated exceptional performance compared to the state-of-the-art work, achieving accuracy rates of 98.61% and 99.3%, respectively. This achievement highlights that our approach not only enhances the security of the federated learning system, but also more effectively accomplishes the detection of Android malware. © 2023 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Frequency Fitness Assignment: Optimization Without Bias for Good Solution Outperforms Randomized Local Search on the Quadratic Assignment Problem 16th

Frequency Fitness Assignment: Optimization Without Bias for ...

引用

16th international Joint conference on Computational intelligence, IJCCI 2024

作者： Chen, Jiayang Wu, Zhize Thomson, Sarah L. Weise, Thomas Institute of Applied Optimization School of Artificial Intelligence and Big Data Hefei University Jinxiu Dadao 99 Anhui Hefei230601 China School of Computing Engineering & the Built Environment Edinburgh Napier University 10 Colinton Road EdinburghEH10 5DT United Kingdom

ISBN: (纸本)9789897587214

The Quadratic Assignment Problem (QAP) is one of the classical N P-hard tasks from operations research with a history of more than 65 years. It is often approached with heuristic algorithms and over the years, a multitude of such methods has been applied. All of them have in common that they tend to prefer better solutions over worse ones. We approach the QAP with Frequency Fitness Assignment (FFA), an algorithm module that can be plugged into arbitrary iterative heuristics and that removes this bias. One would expect that a heuristic that does not care whether a new solution is better or worse compared to the current one should not perform very well. We plug FFA into a simple randomized local search (RLS) and yield the FRLS, which surprisingly outperforms RLS on the vast majority of the instances of the well-known QAPLIB benchmark set. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

The Digital Construction in Multinational Corporations: A Preliminary Study 7

The Digital Construction in Multinational Corporations: A Pr...

引用

7th IEEE international conference on big data intelligence and computing, datacom 2021

作者： Zhang, Zhengkai Xu, Shengzhi State Grid International Development Co. Ltd. Department of Technical Support Beijing China

ISBN: (纸本)9781665420716

The international market environment is undergoing rapid change. To advance the development of multinational corporations, the information systems in multinational corporations are expected to be constructed rapidly and optimized timely in accordance with the requirements of international business management. Moreover, the cross-border data in multinational corporations is massive, from which valuable insights can be discovered to support international business management. In this paper, we analyze the challenges of constructing information systems in multinational corporations. We propose that the new architecture with the enterprise middle platform as core should be used in multinational corporations. This architecture could accumulate common system functions, collect business data resources, and provide convenient and reusable services to the front-end information systems. Based on the enterprise middle platform, we could accelerate the construction of the information systems and conduct various data analysis. An information system is developed as an example to show that adopting this new architecture is good for multinational corporations to implement global management. The study in this paper provides meaningful references for multinational corporations to drive digital transformation. © 2021 IEEE.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Construction of Computer big data Security Technology Platform Based on Artificial intelligence 2

Construction of Computer Big Data Security Technology Platfo...

引用

2nd IEEE international conference on Advanced Technologies in Intelligent Control, Environment, computing and Communication Engineering, ICATIECE 2022

作者： Miao, Yu Chongqing Three Gorges Vocational College Chongqing China

ISBN: (纸本)9781665493963

Artificial technology developed in recent years. It is an intelligent system that can perform tasks without human intervention. AI can be used for various purposes, such as speech recognition, face recognition, etc. AI can be used for good or bad purposes, depending on how it is implemented. The discuss the application of AI in data security technology and its advantages over traditional security methods. We will focus on the good use of AI by analyzing the impact of AI on the development of big data security technology. AI can be used to enhance security technology by using machine learning algorithms, which can analyze large amounts of data and identify patterns that cannot be detected automatically by humans. The computer big data security technology platform based on artificial intelligence in this paper is the process of creating a system that can identify and prevent malicious programs. The system must be able to detect all types of threats, including viruses, worms, Trojans and spyware. It should also be able to monitor network activity and respond quickly in the event of an attack. © 2022 IEEE.

关键词： Intelligent systems

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136页 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：