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

7,500 篇 会议
123 册 图书
85 篇 期刊文献
2 篇 学位论文

馆藏范围

7,710 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,801 篇 工学
- 2,685 篇 计算机科学与技术...
- 1,846 篇 软件工程
- 1,517 篇 信息与通信工程
- 1,048 篇 电气工程
- 434 篇 控制科学与工程
- 423 篇 光学工程
- 396 篇 电子科学与技术（可...
- 305 篇 生物医学工程（可授...
- 288 篇 生物工程
- 277 篇 仪器科学与技术
- 224 篇 机械工程
- 124 篇 网络空间安全
- 123 篇 交通运输工程
- 107 篇 化学工程与技术
- 106 篇 安全科学与工程
- 99 篇 动力工程及工程热...
- 96 篇 材料科学与工程（可...
- 76 篇 建筑学
1,484 篇 理学
- 747 篇 数学
- 560 篇 物理学
- 311 篇 生物学
- 247 篇 统计学（可授理学、...
- 225 篇 系统科学
- 117 篇 化学
544 篇 管理学
- 328 篇 管理科学与工程(可...
- 241 篇 图书情报与档案管...
- 82 篇 工商管理
380 篇 医学
- 351 篇 临床医学
- 161 篇 基础医学(可授医学...
- 109 篇 药学(可授医学、理...
85 篇 法学
51 篇 农学
32 篇 教育学
32 篇 军事学
27 篇 经济学
19 篇 文学
5 篇 艺术学

主题

617 篇 internet of thin...
443 篇 internet
441 篇 image segmentati...
441 篇 feature extracti...
371 篇 signal processin...
364 篇 real-time system...
339 篇 image processing
320 篇 image coding
302 篇 image edge detec...
245 篇 signal processin...
234 篇 image color anal...
209 篇 signal to noise ...
203 篇 cameras
198 篇 accuracy
194 篇 deep learning
185 篇 visualization
161 篇 image reconstruc...
154 篇 image retrieval
148 篇 computational mo...
137 篇 psnr

机构

14 篇 center for signa...
10 篇 university of sc...
10 篇 school of electr...
10 篇 university of el...
10 篇 university of ch...
9 篇 school of cyber ...
9 篇 faculty of infor...
9 篇 signal and infor...
9 篇 signal processin...
9 篇 institute of sig...
9 篇 college of big d...
9 篇 school of comput...
9 篇 hannam universit...
8 篇 tsinghua univers...
8 篇 chitkara centre ...
8 篇 harbin institute...
8 篇 school of intern...
8 篇 school of intern...
7 篇 centre of resear...
7 篇 school of comput...

作者

12 篇 dipanda albert
12 篇 tai-hoon kim
12 篇 wang wei
11 篇 sridha sridharan
11 篇 fan zhun
10 篇 yoshitaka sakura...
10 篇 r.m. mersereau
10 篇 christoph busch
9 篇 hnoohom narit
9 篇 busch christoph
9 篇 li li
9 篇 zhu guijie
9 篇 kutics andrea
8 篇 gwanggil jeon
8 篇 clinton fookes
8 篇 sridharan sridha
8 篇 dominik ślęzak
8 篇 jechang jeong
7 篇 ahmed bouridane
7 篇 jing wang

语言

7,490 篇 英文
199 篇 其他
35 篇 中文
1 篇 土耳其文

检索条件"任意字段=International Conference on Signal Image Technology and Internet Based Systems"

共 7710 条记录，以下是1081-1090 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：

An NFNet-based Approach for Enhanced Bearing Fault Classification Using Vibrational signal Analysis 14

An NFNet-Based Approach for Enhanced Bearing Fault Classific...

引用

14th international conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Jain, Vidhi Dixit, Mayank Misra, Vihaan Bhutani, Geetansh Singh, Vijander Netaji Subhas University of Technology Department of Electrical Engineering Delhi India Netaji Subhas University of Technology Department of Instrumentation and Control Engineering Delhi India

ISBN: (纸本)9798350335095

The present work proposes a novel approach for detecting bearing faults in induction motors using vibrational signals. The proposed method employs a Normalizer-Free ResNet (NFNet) architecture to extract relevant features from 2D image representations of raw vibration data and a classification model to identify the presence of a fault. We convert the vibrational signals into 2D images by applying the Short-Time Fourier Transform (STFT) technique, which offers a time-frequency analysis of the signals. The proposed method improves accuracy over conventional approaches along with reduced computational overhead by using high-performance NFNet architecture for classification. The effectiveness of the proposed method is evaluated on the Case Western Reserve University (CWRU) and Intelligent Maintenance systems (IMS) datasets of vibration signals from induction motors, experiencing various bearing faults. The results indicate that the suggested framework outperforms the existing methods in terms of accuracy and efficiency, achieving state-of-the-art results. This method can be used for real-time monitoring of induction motors to detect bearing faults and prevent potential equipment failures, making it highly useful for industrial applications. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Recognition of Hybrid Digital Watermarking Techniques using Digital image Processing using Deep Learning Techniques 2

Recognition of Hybrid Digital Watermarking Techniques using ...

引用

2nd international conference on Augmented Intelligence and Sustainable systems, ICAISS 2023

作者： Indira, Chilumala Noorullah, R.M. Balguri, Praveen Kumar Pinisetty, Sowjanya Krishna Institute of Aeronautical Engineerring Department of Computer Science and Engineering Dundigal Hyderabad India Institute of Aeronautical Engineerring Department of Aeronautical Engineering Dundigal Hyderabad India University of Electronic Science and Technology of China Institute of Fundamental and Frontier Science Chengdu China

ISBN: (纸本)9798350325799

Digital watermarking is the procedure to identify the source and creator of the data. This is a form of digital media marker such as video, audio or image format. It helps to protect the data from various external unauthorized access. This is done through embedded digital information in the carrier signal to identify ownership and copyright protection. Security and privacy concerns need to be improved due to the rapid increase in the transmission and receiving of digital data. Various sectors such as the navy, military, intelligence, and police are sending and receiving numerous data through online mode. The existing system utilizes Arnold map with QWT-DCT techniques which are unable to obtain invisibility in attack detection. To overcome the limitations of the existing system the proposed system is implemented. They are highly confidential and need to be secured and protected thus hybrid digital watermarking techniques such as nested forms of watermarking are employed. If the third parties tend to make any modification, then it is termed as an attack. The removal of digital watermarking by third parties through certain modifications are denoted through copyright protection application. For security applications and to avoid various types of attacks, Discrete wavelet Transform (DWT) and Non-sampled Contourlet Transform (NSCT) are employed. Security and privacy is obtained through the Quaternion Fourier Transform (QFT) based algorithm with human speech recognition. The pixel displacement with pixel encryption is enhanced to save the privacy of images. Digital watermarking requires security, robustness, watermarking keys and computational cost parameter. Thus to protect the data by neglecting various conventional attacks, digital watermarking techniques are implemented through deep convolutional neural networks. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Solving Non-IID in Federated Learning for image Classification using GANs 20

Solving Non-IID in Federated Learning for Image Classificati...

引用

20th international Joint conference on Computer Science and Software Engineering, JCSSE 2023

作者： Chuenbubpha, Thiti Boonchoo, Thapana Haga, Jason Rattanatamrong, Prapaporn Thammasat University Department of Computer Science Pathum Thani Thailand National Institute of Advanced Industrial Science and Technology Tsukuba Japan

ISBN: (纸本)9798350300505

Federated Learning (FL) has emerged as a powerful methodology for training centralized models while preserving data privacy by using trained parameters from local models that are distributed among decentralized sites. Despite its growing popularity in the development of cloud-based internet of Things (IoT) applications, FL performance is significantly impacted when data is non-independently and identically distributed (non-IID). This paper proposes a novel framework, called GANs Augmented IID - Federated Learning (GAIID-FL) to tackle the diversity of data distribution among clients in FL. The GAIID-FL framework collaboratively trains Generative Adversarial Networks (GANs) and then employs the trained GANs models to generate synthetic data and distribute proportionally to each device. Using GAIID-FL effectively restores the IID data distribution for the setting. The experimental results demonstrate that our framework can achieve up to 45% improvement in accuracy. In addition, the batch collaborative training approach for GANs models can reduce communication overhead by up to 90 times when compared to the unoptimized method. © 2023 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

IoT-based Electrical Device Positioning Method Using Multiple signal Classification and Sparse Bayesian Learning 4

IoT-based Electrical Device Positioning Method Using Multipl...

引用

4th IEEE international conference on Power, Intelligent Computing and systems, ICPICS 2022

作者： Liu, Chang Wang, Yicong Wang, Jin Wang, Jie Tian, Li Yu, Xiao State Grid Hubei Electric Power Research Institute Wuhan China State Grid HBEPC Economic & Technology Research Institute Wuhan China

ISBN: (数字)9781665467735

ISBN: (纸本)9781665467735

Recently, with the increasing service requirement, IoT based electrical device positioning has received much attentions, especially in mixed far-field and near-field sources scenario. In this paper, a new IoT-based positioning algorithm with MUSIC and SBL is proposed. The MUSIC technique is introduced to locate the FF sources at first. And then, an oblique projection is used to isolate near-field sources from the far-field sources. Next, a virtual array output is constructed and SBL is used to find the angle information of the near-field sources. At last, the 1-D searching is used for the range of the NF sources estimation. Our method shows better estimation result than other existing positioning ones © 2022 IEEE.

关键词： internet of things

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer Hashing for image Retrieval

Vision Transformer Hashing for Image Retrieval

引用

2022 IEEE international conference on Multimedia and Expo, ICME 2022

作者： Dubey, Shiv Ram Singh, Satish Kumar Chu, Wei-Ta Indian Institute of Information Technology Computer Vision and Biometrics Lab Allahabad India National Cheng Kung University Dept. of Computer Science and Information Engineering Taiwan

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Recently, Transformer has emerged as a new architecture in deep learning by utilizing self-attention without convolution. Transformer is also extended to Vision Transformer (ViT) for the visual recognition with a promising performance on imageNet. In this paper, we propose a Vision Transformer Hashing (VTS) for image retrieval. We utilize the pre-trained ViT on imageNet as the backbone network and add the hashing head. The proposed VTS model is fine tuned for hashing under six different image retrieval frameworks with their objective functions. We perform the extensive experiments on CIFAR10, imageNet, NUS-Wide, and COCO datasets. The proposed VTS based image retrieval outperforms the recent state-of-the-art hashing techniques with a significant margin. We also find the proposed VTS model as the backbone network is better than the existing networks, such as AlexNet and ResNet. The code is released at https://***/shivram1987/VisionTransformerHashing. © 2022 IEEE.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

Visual Cryptographic Permuted Sampling based Binary image Watermarking 4

Visual Cryptographic Permuted Sampling based Binary Image Wa...

引用

4th international conference on Circuits, Control, Communication and Computing, I4C 2022

作者： Shaik, Ayesha Balasundaram, A. Nivedita, M. School of Computer Science and Engineering Vellore Institute of Technology Chennai Chennai600127 India Center for Cyber Physical Systems School of Computer Science and Engineering Vellore Institute of Technology Chennai Chennai600127 India

ISBN: (纸本)9798350397475

This paper proposes a visual cryptography per-muted scrambling (VCPS) based watermarking method for binary images. Binary image (BI), which has only black and white pixels, has a nature of compact storage. Due to the rapid growth of digital technology, a lot of personal information such as health records, hand-written signatures and certificates;book collections and design drawings;cartoon art sketches are stored as digital documents as BIs (white and black pixels) by scanning them. These BIs are communicated through the internet either for the personal or professional case. Here lies a threat of unauthorized usage of these documents and it is essential to protect them by embedding the watermark (owner information of the binary image). The particularity of the BI makes it more challenging for data hiding because the hiding process is different and only few works are available in this domain. In this paper, the data hiding process is carried out using the coding tables and the encrypted binary watermark shares which is flipped and shuffled using visual cryptography. The proposed technique achieves higher visual quality and less computational cost than the state of the art related techniques. © 2022 IEEE.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

M2Mamba: Multi-Scale in Multi-Scale Mamba for Blind Face Restoration

M2Mamba: Multi-Scale in Multi-Scale Mamba for Blind Face Res...

引用

2024 IEEE international conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Yan, Weidan Shao, Wenze Zhang, Dengyin Nanjing University of Posts and Telecommunications School of Internet of Things Nanjing210003 China Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology Nanjing210003 China

ISBN: (纸本)9798350386226

With the evolution of telemedicine, clean images, especially facial images, are crucial in areas such as symptom evaluation and cosmetic medicine. However, dealing with indiscernible facial images, a condition known as blind degradation, poses a formidable challenge for existing blind face restoration (BFR) techniques due to their inherently ill-posed nature. Thus, a delicate interaction between preserving local details and maintaining global geometries is desired. Despite advances in convolutional neural networks (CNNs), transformers, and denoising diffusion, where no matter serried convolutions, elaborately-designed self-attentions, or stochastic noises, tend to isolate either local or non-local features. To this end, a new candidate model termed Multi-Scale in Multi-Scale Mamba (M2Mamba) is proposed, which builds on a pioneering structured state space model-based network and includes three new components: multi-scale learned fusion module (MSLFM), multi-scale attention fusion module (MSAFM), and multi-scale inspired Mamba (MS-Mamba). Firstly, the MSLFM is adopted by extracting image-level global guidance from inputs of different scales, preserving intuitive perception yet enriching semantic understanding. Secondly, the MSAFM dynamically integrates features from various encoder stages. Thirdly, the MS-Mamba employs separate branches for both small- and large-scale receptive fields, benefiting modeling of long-range dependencies. In the final, M2Mamba is demonstrated on both synthetic and realistic benchmarks, showing comparable or better performance than state-of-the-art methods. The codes are available at: https://***/yanwd628/M2Mamba. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method of Servo Motor Bearing Installation Misalignment based on CSFF-CNN

Fault Diagnosis Method of Servo Motor Bearing Installation M...

引用

international conference on Electrical Machines and systems (ICEMS)

作者： Jing Wang Jianye Li Ming Yang Xinmei Zhang School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China Ningbo Anson CNC Technology Co. Ltd Ningbo China

ISBN: (数字)9784886864406

ISBN: (纸本)9798350379105

As an important part of servo motor, bearing misalignment fault diagnosis has attracted more and more attention. In order to improve the fault diagnosis performance of servo motor gear, a fault diagnosis method based on compressed sensing feature fusion is proposed. In this paper, the alpha phase current is collected and converted into the image by the image transformation method. In order to effectively improve the feature extraction ability of the model for key information, this paper proposes to use the compressed sensing of the signal and the compressed sensing of the signal transformed into the image and the neural network to extract the feature of the original signal transformed into the image. In order to improve the feature extraction ability of the model for multi-gradient information flow, this paper proposed a module named multi-gradient information flow module. The performance of the model proposed in this paper has been verified by the collected servo motor gear data. Under different working conditions, the effect of the method proposed in this paper is improved compared with that of convolution neural network, and the model has strong generalization ability, which proves the superiority of the model performance.

关键词： Fault diagnosis image coding Gears Neural networks Transforms Feature extraction Stability analysis Data mining Servomotors Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Farmland Boundary Extraction technology based on UAV images

Farmland Boundary Extraction Technology Based on UAV Images

引用

international conference on Identification, Information and Knowledge in the internet of Things (IIKI)

作者： Ru Han Lei Shu Zihao Wang Xuying Wang School of Artificial Intelligence Nanjing Agricultural University Nanjing China Guangdong Provincial Key Laboratory for Green Agricultural Production and Intelligent Equipment School of Environmental Science and Engineering Guangdong University of Petrochemical Technology Maoming China

ISBN: (数字)9798331510633

ISBN: (纸本)9798331510640

With the development of 5G and internet of Things, more and more intelligent agricultural products are put into use, such as solar insecticidal lamps, agricultural robots, intelligent irrigation systems. The efficient operation of these intelligent products deployed in farmland depends on the improvement of ridge information. However, in the existing map system, the gap of ridge information has caused great difficulties in laying these nodes. Because it will be an extremely arduous task to use the traditional method to extract the aerial ridge map, so this paper uses the image processing method to extract the ridge information. To solve this problem, We use the edge detection method to extract the ridge. The main steps include image enhancement, image smoothing and edge detection. In this paper, many experiments have been carried out on these three parts, and the best method has been selected. However, because the traditional edge detection operator can not extract the ridge with high precision, this paper optimizes the edge detection results step by step, so as to obtain an algorithm more suitable for ridge extraction and improve the extraction accuracy. At the same time, in view of the large area of cultivated land, unmanned aerial vehicle (UAV) can not get all the images of cultivated land in the case of improving the definition, so it is necessary to stitch the images. Therefore, this paper mainly expounds the basic principles of image stitching based on feature points and image stitching based on regions, and selects an algorithm suitable for stitching farmland images through experimental verification. Finally, through the research of this paper, the vacancy of ridge information can be made up to some extent, and the workload of manual measurement can be reduced.

关键词： Irrigation Agricultural robots Accuracy Smoothing methods image edge detection Autonomous aerial vehicles Data mining internet of Things image stitching image enhancement

来源：评论

学校读者我要写书评

暂无评论

Enhanced Data Hiding based on First, Middle, and Last Order Pixel in Spatial Domain images

Enhanced Data Hiding Based on First, Middle, and Last Order ...

引用

international conference on signal Processing and Communication (ICSC)

作者： Rahmad Hidayat Adifa Widyadhani Chanda D'Layla Ntivuguruzwa Jean De La Croix Tohari Ahmad Department of Informatics Institut Teknologi Sepuluh Nopember Surabaya Indonesia STAIN Sultan Abdurrahman Kepulauan Riau Indonesia Department of Informatics Institut Teknologi Sepuluh Nopember Surabaya Indonesia University of Rwanda Kigali Rwanda Department of Informatics Intitut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

The rapid advancement of internet technology has revolutionized global information sharing, enabling faster and more efficient digital communication. However, the increased reliance on online platforms for exchanging sensitive information raises significant concerns about data security, as unauthorized access and misuse of transmitted data pose severe risks, including identity theft and financial fraud. Steganography has emerged as a promising technique for securing data by embedding it imperceptibly into digital media. This study introduces a novel steganographic method that utilizes the difference between pixels in the cover image to embed secret messages while maintaining high image quality. The proposed scheme divides image pixels into blocks of 9. It calculates the difference between pixels with each block's first, middle, or last pixel to ensure minimal distortion and superior visual quality post-embedding. Experimental results validate the effectiveness of the method, achieving consistently higher PSNR (Peak signal-to-Noise Ratio) values compared to a baseline approach, with a PSNR of 64.9205 dB for a 10 KB payload and similarly superior results for payloads of 20 KB and 40 KB.

关键词： image quality Steganography Visualization PSNR Scalability Media Distortion Robustness internet Payloads

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 << < 105 106 107 108 109 110 111 112 113 114 > >>

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：