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

40,510 篇 会议
107 篇 期刊文献
97 册 图书

馆藏范围

40,714 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

23,085 篇 工学
- 19,883 篇 计算机科学与技术...
- 17,994 篇 软件工程
- 7,869 篇 信息与通信工程
- 7,818 篇 生物工程
- 4,852 篇 控制科学与工程
- 3,903 篇 生物医学工程（可授...
- 2,982 篇 电气工程
- 2,742 篇 光学工程
- 1,929 篇 网络空间安全
- 1,860 篇 电子科学与技术（可...
- 1,634 篇 安全科学与工程
- 1,451 篇 机械工程
- 1,427 篇 交通运输工程
- 1,359 篇 动力工程及工程热...
- 1,266 篇 化学工程与技术
14,261 篇 理学
- 8,024 篇 生物学
- 6,082 篇 数学
- 3,070 篇 物理学
- 2,810 篇 统计学（可授理学、...
- 1,467 篇 系统科学
- 1,463 篇 化学
7,498 篇 管理学
- 4,229 篇 图书情报与档案管...
- 3,686 篇 管理科学与工程(可...
- 2,017 篇 工商管理
3,605 篇 医学
- 3,123 篇 临床医学
- 3,077 篇 基础医学(可授医学...
- 2,390 篇 药学(可授医学、理...
- 1,391 篇 公共卫生与预防医...
1,563 篇 法学
- 1,390 篇 社会学
1,287 篇 教育学
- 1,283 篇 教育学
1,126 篇 农学
806 篇 经济学
283 篇 文学
53 篇 军事学
2 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

2,380 篇 deep learning
1,940 篇 machine learning
823 篇 support vector m...
640 篇 convolutional ne...
566 篇 training
546 篇 feature extracti...
536 篇 forecasting
478 篇 computational mo...
467 篇 reinforcement le...
460 篇 machine learning...
456 篇 object detection
421 篇 computer vision
413 篇 neural networks
409 篇 internet of thin...
394 篇 predictive model...
355 篇 covid-19
332 篇 long short-term ...
309 篇 transfer learnin...
258 篇 convolution
256 篇 image segmentati...

机构

471 篇 chitkara univers...
135 篇 computer science...
126 篇 school of comput...
88 篇 karnataka bangal...
85 篇 college of compu...
83 篇 centre of interd...
67 篇 school of comput...
61 篇 school of comput...
58 篇 school of comput...
58 篇 graphic era deem...
53 篇 department of co...
50 篇 medical technica...
49 篇 computer science...
48 篇 school of comput...
47 篇 maharishi school...
46 篇 department of co...
43 篇 computer science...
43 篇 the islamic univ...
42 篇 department of co...
41 篇 school of comput...

作者

61 篇 shiva mehta
49 篇 sharma vikrant
40 篇 anjali t.
37 篇 vinay kukreja
34 篇 rakesh kumar
30 篇 deepak gerard
29 篇 sharma neha
27 篇 gill kanwarparta...
25 篇 vishal jain
25 篇 sheshang degadwa...
25 篇 li li
25 篇 nagaraj p.
24 篇 rishabh sharma
24 篇 kukreja vinay
22 篇 pareek piyush ku...
22 篇 shanmugasundaram...
21 篇 yu wang
21 篇 dhairya vyas
20 篇 kumar manish
20 篇 p nagaraj

语言

39,100 篇 英文
1,600 篇 其他
377 篇 中文
4 篇 葡萄牙文
3 篇 西班牙文
1 篇 德文
1 篇 土耳其文

检索条件"任意字段=2023 International Conference on Computer Engineering and Distance Learning, CEDL 2023"

共 40714 条记录，以下是4821-4830 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：

SCALE-UP: AN EFFICIENT BLACK-BOX INPUT-LEVEL BACKDOOR DETECTION VIA ANALYZING SCALED PREDICTION CONSISTENCY 11

SCALE-UP: AN EFFICIENT BLACK-BOX INPUT-LEVEL BACKDOOR DETECT...

引用

11th international conference on learning Representations, ICLR 2023

作者： Guo, Junfeng Li, Yiming Chen, Xun Guo, Hanqing Sun, Lichao Liu, Cong Department of Computer Science UT Dallas United States Tsinghua Shenzhen International Graduate School Tsinghua University China Samsung Research America Mountain View United States Department of Computer Science Michigan State University United States Department of Computer Science Lehigh University United States Department of Electricity and Computer Engineering Department UC Riverside United States

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of DNNs under the real-world machine learning as a service (MLaaS) setting, where the deployed model is fully black-box while the users can only query and obtain its predictions. Currently, there are many existing defenses to reduce backdoor threats. However, almost all of them cannot be adopted in MLaaS scenarios since they require getting access to or even modifying the suspicious models. In this paper, we propose a simple yet effective black-box input-level backdoor detection, called SCALE-UP, which requires only the predicted labels to alleviate this problem. Specifically, we identify and filter malicious testing samples by analyzing their prediction consistency during the pixel-wise amplification process. Our defense is motivated by an intriguing observation (dubbed scaled prediction consistency) that the predictions of poisoned samples are significantly more consistent compared to those of benign ones when amplifying all pixel values. Besides, we also provide theoretical foundations to explain this phenomenon. Extensive experiments are conducted on benchmark datasets, verifying the effectiveness and efficiency of our defense and its resistance to potential adaptive attacks. Our codes are available at https://***/JunfengGo/SCALE-UP. © 2023 11th international conference on learning Representations, ICLR 2023. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Using Deep learning and MobileNet50V2 CNN Model to Classify Chest X-Ray Images for Pneumonia Disease Detection 2

Using Deep Learning and MobileNet50V2 CNN Model to Classify ...

引用

2nd IEEE international conference on Futuristic Technologies, INCOFT 2023

作者： Gill, Kanwarpartap Singh Anand, Vatsala Chauhan, Rahul Rawat, Devyani Gupta, Rupesh Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Hill University Computer Science and Engineering Punjab India Graphic Era Deemed to Be University Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350308846

Pneumonia is a pathological condition characterised by the inflammation of the alveoli in either one or both lungs. Symptoms including productive cough, fever, chills, and dyspnea may develop when fluid or purulent material builds up within the air sacs. Many different kinds of organisms, such as bacteria, viruses, and fungi, may cause pneumonia. Pneumonia may range in intensity from quite mild to severe. The population groups most vulnerable to this condition are newborns and young children, those aged 65 and above, as well as those with underlying health conditions or compromised immune systems. This research focuses on the categorization of pneumonia sickness by using the MobileNet50V2 Model and exploiting chest X-ray images. The primary objective is to enhance the accuracy of the classification process. The use of artificial intelligence in the medical sector is seen as a significant and auspicious application. The research further proposes strategies to augment the current practises used by the medical community. It is important to consider that the development of a pneumonia classification model necessitates the integration of deep learning techniques, medical imaging expertise, and domain knowledge proficiency. In order to ensure the clinical validity and safety of the model, it is essential to engage in collaborative efforts with medical professionals. © 2023 IEEE.

关键词： Classification CNN Confusion matrix Deep learning MobileNet50V2 Model Model Training Pneumonia Disease

来源：评论

学校读者我要写书评

暂无评论

Latency-aware SDN-based Mobile Edge Computation Offloading in Industrial IoT 28

Latency-aware SDN-based Mobile Edge Computation Offloading i...

引用

28th international computer conference, computer Society of Iran, CSICC 2023

作者： Hoseini, Seyyed Shayan Beyer, Tebbo Ghaderi, Ali Movahedi, Zeinab School of Computer Engineering Iran Uiniversity of Science and Technology Tehran Iran Kiel University Department of Computer Science Kiel Germany

ISBN: (纸本)9798350338195

Industrial Internet of things (IIoT) is a promising architecture for cyber-physical systems. Although it brings a vast number of different advantages, it enables some severe challenges as well, such as energy consumption and delay management. Due to producing a big amount of raw sensing data and the demands for processing them, various computation offloading methods over different infrastructures have been proposed. Mobile Edge Computing (MEC) is one of those infrastructures being able to give the required execution power at a much closer distance from the end devices. Software Defined Networking (SDN) is set to provide a programmable interface that can be used to manage a network of MECs in order to choose the optimal MEC for the received offloading requests. In this paper, we proposed a latency-aware SDN-based computation offloading method with specific communication, computation, and energy consumption models which aim at optimizing the overall response time. Results show that with having a delay threshold, a significant number of resources will be freed and as a result, overall response time will be decreased. © 2023 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

learning Spatial and Geometric Information for Robust Features 3

Learning Spatial and Geometric Information for Robust Featur...

引用

3rd international conference on Consumer Electronics and computer engineering, ICCECE 2023

作者： Zhou, Junqi Li, Yanfeng Chen, Houjin School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

ISBN: (纸本)9798350331578

Robust local feature detection and description are crucial in a huge of computer vision tasks. However, current feature descriptors lack geometric information and spatial features. In this paper, we propose a novel spatial and geometric feature fusion architecture, which can effectively tackle these problems. The proposed architecture includes three aspects. 1) A multiple low-level feature fusion (ML2F2) subnetworks, which could improve the ability to extract geometric information through the weighted fusion features. 2) A subnetwork for gradient feature extraction (GFE) which could validly extract the spatial features by encoding the horizontal and vertical gradients of an image. 3) Effective spatial geometric feature fusion (SGFF) module to alternatively fuse the above subnetworks. Experiments on the task of Image Matching and Long-Term Visual Localization show that the proposed method is superior to most advanced local feature descriptors. © 2023 IEEE.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

The Construction of an Intelligent Water Environment Automatic Monitoring System Based on the Internet of Things

The Construction of an Intelligent Water Environment Automat...

引用

2023 international conference on Intelligent Systems, Communications, and computer Networks, ISCCN 2023

作者： Zhao, Weichen Wu, Shouyuan School of Electrical Engineering Shandong University Jinan Shandong250061 China

ISBN: (纸本)9781510666238

To solve the traditional water quality detection using ZigBee, GPRS, and other communication technologies having limited coverage distance, high power consumption, high cost, and complex deployment problems, according to the water quality testing real-Time monitoring requirements, an NB-IoT-based water quality monitoring system platform is designed. The system uses the "end-Tube-cloud" of the Internet of things mode, through the temperature, pH, dissolved oxygen, and other sensors to collect water quality parameters. M5310-A module will receive the sensor data uploaded to the OneNET cloud platform to achieve the remote transmission of water quality information and display functions, while the user can be in the application terminal real-Time monitoring and directly read the water quality parameters of the measured waters. The system effectively improves the efficiency and modernization of water quality monitoring work, with good application prospects and economic benefits. © 2023 SPIE. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Advancing Political Bias Detection: A Novel High-Accuracy Model

Advancing Political Bias Detection: A Novel High-Accuracy Mo...

引用

2023 international conference on Computational Intelligence and Sustainable engineering Solution, CISES 2023

作者： Sharma, Manan Kashyap, Krishanu Gupta, Kushagra Kumar, Shailender Delhi Technological University Department of Computer Science & Engineering New Delhi India

ISBN: (纸本)9798350323917

Media bias is a persistent departure from the core values of objectivity and accuracy in journalism. Instead of presenting the facts objectively, media outlets and reporters frequently choose the storylines and specifics that will be included in their articles. Whether established or learned, biases have the power to dramatically influence people's views and attitudes in different societies and regions, which can lead to skewed assessments. This study intends to address the issue of biased and closed-minded attitudes in the media by introducing a novel approach leveraging deep learning. This approach beats the previous state-of-the-art models on accuracy on multiple datasets to identify political bias in the media. By highlighting these biases in political reporting we aim to offer a more unbiased evaluation of media coverage. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Object Detection in YOLOv5 Remote Sensing Images Based on Reparameterization 2

Object Detection in YOLOv5 Remote Sensing Images Based on Re...

引用

2nd international conference on Image Processing, computer Vision and Machine learning, ICICML 2023

作者： Xie, Xuan Kang, Li Zhang, Junshen Xie, Keqiang Dongguan University of Technology School of Computer Science and Technology GuangDong DongGuan China Dongguan University of Technology School of Electrical Engineering and Intelligentization GuangDong DongGuan China

ISBN: (纸本)9798350331417

An improved object detection algorithm based on Yolov5s is proposed for the characteristics of remote sensing images with many types of features, dense objects and complex background. Firstly, the idea of reparameterization is applied in the backbone network to reduce the computational amount of network detection;secondly, the Efficient Channel Attention (ECA) mechanism is applied in the Yolov5s backbone network, which is used to enhance the feature extraction ability of the network;finally, the second layer of the backbone network is replaced by the Dilated convolution with a larger perceptual field under the same number of parameters. The experimental results show that the algorithm in this paper achieves an accuracy of 72.90% on the DOTA dataset, which is 1.76% higher than the mean accuracy (mAP) of Yolov5s, and the computational GFLOPS ranges from 17.4 to 17.5, which is a large improvement in accuracy obtained with only a small number of parameter additions compared to Yolov5s. © 2023 IEEE.

关键词： Object Detection Remote Sense Reparameterization Yolov5

来源：评论

学校读者我要写书评

暂无评论

Advanced Threat Intelligence Forecasting using Machine learning Algorithms 3

Advanced Threat Intelligence Forecasting using Machine Learn...

引用

3rd IEEE international conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Kumhar, Bhupchand Saxena, Antima Nagar, Mayank Ies University Department of Computer Science & Engineering Madhya Pradesh Bhopal462044 India Ies College of Technology Department of Electronics & Communication Engineering Madhya Pradesh Bhopal462044 India

ISBN: (纸本)9798350343274

This section introduces an innovative approach for advanced threat intelligence forecasting employing machine learning algorithms. The proposed method integrates three powerful algorithms - Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM), and elucidates the foundational mathematical concepts. The process commences with data preprocessing involving cleaning, normalization, and feature engineering to prepare the raw data for machine learning. Subsequently, Principal Component Analysis (PCA) is employed for optimal feature selection. The integration of Random Forest, SVM, and LSTM algorithms forms a robust predictive framework. Random Forest, known for its accuracy and versatility, constructs an ensemble of decision trees, ensuring reliable classification. SVM seeks the optimal hyperplane to effectively separate classes in feature space, proving valuable in complex, non-linearly separable data scenarios. LSTM, a type of recurrent neural network, excels in capturing long-term dependencies in sequential data, making it indispensable in threat intelligence. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Indian National Stock Exchange Crude Oil (CL=F) Close Price Forecasting Using LSTM and Bi-LSTM Multivariate Deep learning Approaches

Indian National Stock Exchange Crude Oil (CL=F) Close Price ...

引用

2023 international conference on Computational Intelligence and Sustainable engineering Solution, CISES 2023

作者： Khullar, Vikas Chhabra, Rishu Angurala, Mohit Veeramanickam, M.R.M. Singh, Kirandeep Lamba, Vikas Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India

ISBN: (纸本)9798350323917

Predictive analysis of crude oil prices is very much required as worldwide economy depends on it. In this paper, time series based predictive analysis is implemented to predict crude oil prices in Indian national stock exchange. A real time online data source was utilized for collecting till date data starting from 2002. LSTM and Bidirectional-LSTM based multivariate algorithms were applied to analyze and predict future trends and predictions of fuel prices. Analyzed results on crude oil price prediction revealed Bi-LSTM as a better technique in comparison to LSTM. © 2023 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Hybrid Feature Extraction Based Deep learning Model for Offline Signature Verification 6

Hybrid Feature Extraction Based Deep Learning Model for Offl...

引用

6th international conference on Software engineering and computer Science, CSECS 2023

作者： Xiong, Tong Zhang, Xin School of Electronic and information Engineering South China University of Technology GuangZhou China

ISBN: (纸本)9798350306378

Offline signature verification serves as a robust authentication method, widely adopted in security applications due to its non-intrusive data collection procedure. Despite the notable advancements in this filed for the past several years, effectively representing signature traits remains challenging. Existing methods rely on handcrafted features or Convolutional Neural Networks (CNN) for visual learning to achieve this goal. Yet, they tend to overlook the intricate nature of signatures, primarily treating them as images while neglecting their multifaceted composition, encompassing continuous curves and strokes. To transcend this limitation, we present a novel hybrid feature extraction based deep learning model for offline signature verification. Considering the implied temporal nature of offline signature, we partition signature images into multiple subregions to extract local features, and then utilize Recurrent Neural Network (RNN) to model the contextual connections between these subregions. For each subregion, we extract corresponding contours features and texture features to exploit the stroke trajectory and static image characteristics of offline signatures. These extracted hybrid features facilitate authentication through following Writer-Dependent classifiers. We evaluate the proposed method on three widely-used datasets, i.e., CEDAR, BHSig-H and BHSig-B. The experimental results indicate that the proposed model can comprehensively represent the input signature, validating its effectiveness. On BHSig-H and BHSig-B, our model improves the performance with equal error rates of 4.61%, 1.49% respectively, compared to 5.65%, 3.96% achieved by previous state-of-the-art methods. © 2023 IEEE.

关键词： Textures

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 << < 479 480 481 482 483 484 485 486 487 488 > >>

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：