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

771 篇 会议
25 册 图书
5 篇 期刊文献

馆藏范围

801 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

551 篇 工学
- 438 篇 计算机科学与技术...
- 255 篇 控制科学与工程
- 228 篇 信息与通信工程
- 216 篇 电气工程
- 201 篇 软件工程
- 180 篇 动力工程及工程热...
- 180 篇 安全科学与工程
- 172 篇 网络空间安全
- 170 篇 仪器科学与技术
- 169 篇 交通运输工程
- 32 篇 机械工程
- 32 篇 生物工程
- 30 篇 电子科学与技术（可...
- 20 篇 化学工程与技术
- 19 篇 生物医学工程（可授...
- 17 篇 光学工程
300 篇 理学
- 177 篇 化学
- 68 篇 数学
- 38 篇 物理学
- 36 篇 生物学
- 17 篇 统计学（可授理学、...
- 12 篇 系统科学
248 篇 管理学
- 217 篇 管理科学与工程(可...
- 194 篇 图书情报与档案管...
- 35 篇 工商管理
25 篇 教育学
- 25 篇 教育学
23 篇 医学
- 23 篇 临床医学
- 22 篇 基础医学(可授医学...
22 篇 法学
- 19 篇 社会学
13 篇 经济学
- 13 篇 应用经济学
6 篇 农学
3 篇 军事学
2 篇 文学

主题

106 篇 smart cities
38 篇 deep learning
38 篇 computational mo...
38 篇 training
37 篇 computer archite...
26 篇 costs
26 篇 feature extracti...
23 篇 semantics
21 篇 data models
20 篇 predictive model...
20 篇 machine learning
19 篇 artificial intel...
19 篇 computer vision
17 篇 reinforcement le...
17 篇 visualization
16 篇 heuristic algori...
15 篇 servers
15 篇 hardware
14 篇 real-time system...
13 篇 internet of thin...

机构

13 篇 school of comput...
10 篇 college of compu...
8 篇 school of comput...
6 篇 university polit...
5 篇 school of automa...
5 篇 college of busin...
5 篇 university polit...
5 篇 school of comput...
4 篇 college of compu...
4 篇 faculty of infor...
4 篇 school of comput...
4 篇 school of comput...
4 篇 faculty of busin...
4 篇 school of comput...
4 篇 university of ch...
4 篇 novosibirsk stat...
4 篇 college of compu...
3 篇 dept. of theoret...
3 篇 robai-lab hainan...
3 篇 electrical power...

作者

8 篇 duan yucong
7 篇 peng jun
6 篇 jin hai
5 篇 houhamdi zina
5 篇 athamena belkace...
4 篇 jiang fu
4 篇 li heng
4 篇 mocanu mariana
4 篇 kashef rasha
4 篇 nobuhiro ito
4 篇 tetsushi wakabay...
4 篇 harous saad
4 篇 takeshi uchitane
4 篇 kazunori iwata
3 篇 wang lei
3 篇 khusnutdinov ale...
3 篇 vadim z. manusov
3 篇 trubák kamil
3 篇 yu zhiwen
3 篇 liu weirong

语言

769 篇 英文
31 篇 其他
8 篇 中文
1 篇 俄文

检索条件"任意字段=23rd International Conference on Computer Systems and Technologies, CompSysTech 2022"

共 801 条记录，以下是171-180 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：

Study on Active Defense of Honeypot-Based Industrial Control Network 23

Study on Active Defense of Honeypot-Based Industrial Control...

引用

23rd IEEE international conference on High Performance Computing and Communications, 7th IEEE international conference on Data Science and systems, 19th IEEE international conference on Smart City and 7th IEEE international conference on Dependability in Sensor, Cloud and Big Data systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Wei, Xunsi Yang, Dequan Beijing Institute of Technology School of Computer Beijing100081 China Network Information Technology Center Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781665494571

With the rapid development of information, network security and information have played an increasingly important role in national production. As a result, the environment and application of industrial control networks are under more and more network security threats. Furthermore, most applications of industrial control networks belong to critical infrastructure, so to guarantee the security of industrial control networks has become more significant, and the defense of it is one of the essential issues in need of being solved. This paper focuses on studying the active protection for the security of industrial control networks and discusses the role of honeypot in the network security for the defense strategy of the industrial control network. Firstly, this paper introduces the theoretical knowledge of honeypots. Secondly, it analyzes the existing problems and development prospects of the honeypot. And finally, under the background of the industrial control network, it designs the SSH honeypot based on Transmission Control Protocol/Internet Protocol (TCP/TP), which is divided into two modules, including SSH information collection and alarm. This system can deploy based on the Docker of Linux. Through simulation practice, it proves that honeypot can effectively capture the attackers' attack and make an early warning to improve network security. © 2021 IEEE.

关键词： Industrial control Linux TCPIP Production Network security Critical infrastructure

来源：评论

学校读者我要写书评

暂无评论

Experience-based Pickup Area Recommendation on Taxi's GPS Trajectories 23

Experience-based Pickup Area Recommendation on Taxi's GPS Tr...

引用

作者： Liao, Zhuhua Zhang, Jian Yi, Aiping Liu, Yizhi Zhao, Yijiang Liu, Silin School of Computer Science & Engineering Hunan University of Science & Technology Xiangtan China

ISBN: (纸本)9781665494571

Experienced drivers can generally earn high income and save more energy and time with their effective experiences. So the behaviors of experienced drivers are important for pickup area recommendation to ordinary drivers. In this paper, we proposed a pickup area recommendation model that considering the behaviors mining of experienced drivers and recommending directions where clustering high profit pickup areas by using taxi's GPS trajectories. Although this is a strategically important task in passenger seeking for taxi drivers, the problem has not been solved due to two major challenges. The one is data sparsity. The other is how to fuse the experiences of professional drivers to recommender. To address these challenges, we firstly fuse the geographic information into the process of filling up the absence data. Then, we make driving direction decision and pickup areas recommendation at any place according to the experiences of experienced drivers. We evaluate our method by using GPS trajectories generated by more than 13000 taxis over a period of one month. The results demonstrate the efficiency of pickup area recommendation for ordinary drivers. © 2021 IEEE.

关键词： Training Fuses Social networking (online) Telecommunication traffic Trajectory Behavioral sciences Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Performance of Liquid State Machine with Time-Division Sampling and Reservoir Reconstructing 23

Enhancing the Performance of Liquid State Machine with Time-...

引用

作者： Qiu, Yuchen Wang, Lei Chen, Xiaofan Qu, Lianhua College of Computer Science and Technology National University of Defense Technology Changsha China

ISBN: (纸本)9781665494571

Remarkable progress has been made over the past few years on the performance of Spiking Neural Network (SNN), which is mostly driven by its biological features and used for pattern classification. However, the existing works on SNNs are challenged by high network complexity and training cost. As motivated by neuromorphic computation and certain features of human brains, Liquid State Machine (LSM) is put forward as a particular form of SNNs. LSMs are characterized by its short-term memory and lightweight computing, which is mostly contributed by its recurrently and randomly connected structure. In this paper, we proposed an improved LSM model on speech recognition using two promising techniques: time-division sampling and reservoir reconstruction. First, we proposed that dividing the output state from the liquid layer through multiple time windows, this approach is proven to explore more detailed input signal information. Second, the reconstructed structure of LSMs is investigated to extend the classification ability of LSMs, and two kinds of topologies of LSMs are served on the basis of parallel assembled liquids and a hub topology. FSDD and N-TIDIGITS datasets are used to demonstrate the performance improvement of proposed methods. Specifically, the classification accuracy of FSDD and N-TIDIGITS are 92%, 87%, respectively. © 2021 IEEE.

关键词： Training Liquids Smart cities Computational modeling Speech recognition Reservoirs Topology

来源：评论

学校读者我要写书评

暂无评论

GNAS: Generalized Neural Attentive Similarity Model for Recommendation 23

GNAS: Generalized Neural Attentive Similarity Model for Reco...

引用

作者： Cheng, Zhilin Lyu, Yanxia Liu, Jiemin Wang, Cong School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China

ISBN: (纸本)9781665494571

Item-based collaborative filtering captures user preferences by using the historical interactive items of users and generates a personalized recommendation list. Recently, the state-of-the-art collaborative filtering method is neural attentive item similarity model (NAIS). However, the exploration of ensemble models has obtained less investigation. In this work, we present a generalized neural attentive similarity (GNAS) model to perform recommendation based on implicit feedback. The key of our design is to integrate the generalized matrix factorization model and neural attentive item similarity model, which allows the model to have both the memorization ability from matrix factorization model and the generalization ability from neural model. To improve the user interest expression ability of the model, we add an ensemble kernel to the attention mechanism, learning the attention weight of historical items that users have interacted with before. Experimental results show that the recommended accuracy of our model is improved compared to the latest recommended models. In addition, GNAS also has the advantage of less time consumption and interpretability of recommendation. © 2021 IEEE.

关键词： Weight measurement Smart cities Collaborative filtering Diversity reception Decision making Collaboration Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Blind Image Quality Assessment Based On Multi-scale Spatial Pyramid Pooling 23

Blind Image Quality Assessment Based On Multi-scale Spatial ...

引用

作者： Lu, Fangfang Qin, Feng Chen, Jingjing College of Computer Science and Technology Shanghai University of Electric Power Shanghai China Zhijiang College Zhejiang University of Technology Shaoxing China

ISBN: (纸本)9781665494571

The current state-of-the-art image quality assessment (IQA) methods are based on convolutional neural networks (CNNs). However, due to the constraint of the feature size by the fully connected layer, the original image must be cropped or stretched into a fixed-size (e.g., 224 x 224) before input into the CNN, which destroys the original structure and content of the image, thus affects the prediction accuracy of the quality score. In this paper, we propose a blind image quality evaluation method based on multi-scale spatial pyramid pooling (named CSPP-IQA). CSPP structure is proposed to fix the semantic feature size, the model can get its quality score by directly inputting the entire image avoid cropping or stretching. Moreover, with the help of introducing the CBAM attention mechanism and adaptive content understanding module, the proposed model improves the prediction accuracy, generalization ability and speed compared with state-of-the-art IQA methods. Experimental results show that the proposed algorithm can accurately and quickly predict the image quality of real scene images. © 2021 IEEE.

关键词： Image quality Training Adaptation models Visualization Computational modeling Semantics Predictive models

来源：评论

学校读者我要写书评

暂无评论

An Energy Dispatch Mechanism Based on Double Auction with Multiple Rounds for a Microgrid 23

An Energy Dispatch Mechanism Based on Double Auction with Mu...

引用

作者： Liu, Weirong Ma, Cheng Cheng, Yijun Jiang, Fu Rong, Jieqi Peng, Jun School of Computer Science and Engineering Central South University Changsha China School of Automation Central South University Changsha China

ISBN: (纸本)9781665494571

In a microgrid, distributed energy resources (DERs) can supply energy for consumers. How to schedule energy between DERs and consumers and reduce the dependence on the main power grid is of extreme importance for a microgrid. In this paper, a multi-round double auction mechanism is proposed to achieve coordinated and optimal energy dispatch, which allows multiple sellers to trade energy with multiple buyers through adjusting prices dynamically in each round until the buyers' bids are not less than the sellers' asks. Different from existing auctions, the excessive energy of one seller can be divided and traded to multiple buyers, and one buyer can purchase the energy from multiple sellers. The simulation results show that the proposed mechanism significantly reduces auction rounds and the dependence on the main power grid and improves auction utility when compared with the existing double auction. © 2021 IEEE.

关键词： Schedules Smart cities Energy resources Simulation Microgrids Distributed power generation Resource management

来源：评论

学校读者我要写书评

暂无评论

RF Transmitter Identification and Classification Based on Deep Residual Shrinkage Network 23

RF Transmitter Identification and Classification Based on De...

引用

作者： Wen, Xiuhua Cao, Chunjie Sun, Yang Li, Yifan Peng, Haifeng Wang, Mengnan Hainan University School of Cryptography Haikou China Hainan University School of Computer Science and Technology Haikou China

ISBN: (纸本)9781665494571

Traditional specific emitter identification (SEI) methods need to artificially design extraction methods of the signal fingerprint features, which require a large amount of calculation and low classification accuracy. A supervised SEI framework based on deep residual shrinkage Network (DRSN) is proposed in this paper, which is used to adaptively learn the deep features of transmitted signals and classify them. In our framework, soft thresholding is introduced to reduce the noise of the original I/Q signal which contains a lot of noise, so as to reduce the influence of noise on the inaccuracy of RF fingerprint feature extraction. The I/Q signal of the receiver is sliced and spliced (pre-processing step) before inputting to the DRSN model to reduce the computational complexity. The experimental results show that the proposed scheme can correctly distinguish 16 credible transmitters with 98% accuracy respectively. Compared with the existing SEI methods, our scheme has the advantages of excellent identification accuracy and strong anti-interference ability. © 2021 IEEE.

关键词： Radio frequency Wireless communication Performance evaluation Design methodology Radio transmitters Receivers Fingerprint recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Comorbidity Analysis in Brain Disorders Reveals Better Diagnosis 23

Efficient Comorbidity Analysis in Brain Disorders Reveals Be...

引用

作者： Li, Menglu Amirizaniani, Maryam Kashef, Rasha Electrical Computer and Biomedical Engineering Ted Rogers School of Management Ryerson University Toronto Canada

ISBN: (纸本)9781665494571

Nowadays, brain disorders are gaining momentum faster than ever. Early detection of these disorders would be helpful in the treatment process. Also, detecting some comorbid brain disorders would be expensive and time-consuming. With advancements in machine learning (ML) and Artificial intelligence, these brain disorders and their comorbidities can be detected in the early stage. Different techniques of machine learning are used to detect Autism Spectrum Disorder (ASD), Attention deficit hyperactivity disorder (ADHD), Intellectual Disability (ID), and other brain disorders. This paper focuses on predicting ASD, ADHD, ID, and their Comorbidities via multi-stage analytical and prediction modelling. The first stage involves efficient data pre-processing. The next stage is a comorbidity analysis phase via logistic regression. In this analysis, logistic regression was applied to recognize health-related variables which are associated with ASD+ADHD+ID. These variables are Vision Test, Brain Injury, Anxiety, Down Syndrome, Blood Disorder, and Cystic Fibrosis. In the third stage, machine learning methods predict ASD, ADHD, ID for better diagnosis. For this purpose, SVM, KNN, and MLP are used. To evaluate these models, accuracy, precision, recall, and F1-score are selected. © 2021 IEEE.

关键词： Support vector machines Autism Smart cities Anxiety disorders Machine learning Predictive models Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Research on Cross-Camera Person Re-Identification Using Overlapping Field of View 23

Research on Cross-Camera Person Re-Identification Using Over...

引用

作者： Zhao, Zhibin Yao, Yinuo Chen, Huicheng Wang, Jun Yan, Yongming School of Computer Science and Engineering Northeastern University Shenyang China Dixin Artificial Intelligence Industry Research Institute Co. Ltd. Shenyang China

ISBN: (纸本)9781665494571

Person re-identification in cross-camera images involves matching the identical individual from a secondary camera filmed frame with a post-identified ID. In a practically public scenario, multiple view angles from different cameras may change greatly, and accordingly the person appearance features between disparate images are quite different. It affects appearance feature-based person re-identification adversely. In this paper, we propose an algorithm that matches location features in images from diverse devices and therefore captures spatial mapping matrix for dual-view overlapping portions. Person's location feature is mapped crossing cameras based on the environment he is in. The Siamese Network is leveraged for appearance similarity calculation. The location similarity and appearance similarity are fused for person re-identification. Solid cross-camera videos are adopted as experimental dataset. Experimental results show the algorithm's effectiveness in cross-camera person re-identification with overlapping field of view. © 2021 IEEE.

关键词： Smart cities Cameras Solids Videos

来源：评论

学校读者我要写书评

暂无评论

Few-shot malicious traffic classification based on Siamese Neural Network 23

Few-shot malicious traffic classification based on Siamese N...

引用

作者： Wu, Kailin Wang, Pan Wang, ZiXuan School of Modern Posts Nanjing University of Posts & Telecommunications Nanjing China

ISBN: (纸本)9781665494571

The process of learning good features for machine learning applications can be computationally expensive, and can prove difficult when there is little data available. A typical example is few-shot learning. In this case, we must make predictions correctly and only give a few examples of each class. In this article, we propose a method based on a one-dimensional convolutional siamese neural network, which uses a unique structure to naturally rank the similarities between inputs. Once the network is adjusted, we can use powerful discriminative features to extend the network's predictive capabilities to new data, and to new categories from unknown distributions. Using the convolutional architecture, we can achieve powerful results that exceed other deep learning models, and have close to the most advanced performance on few-shot classification tasks. The results show that this method can obtain higher recognition accuracy than the traditional methods of smote and GAN generated data training. © 2021 IEEE.

关键词： Training Deep learning Neural networks computer architecture Generative adversarial networks Task analysis

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81页 << < 14 15 16 17 18 19 20 21 22 23 > >>

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：