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

1,313 篇 会议
11 篇 期刊文献
9 册 图书

馆藏范围

1,333 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

901 篇 工学
- 745 篇 计算机科学与技术...
- 487 篇 软件工程
- 302 篇 信息与通信工程
- 204 篇 电气工程
- 175 篇 生物工程
- 126 篇 生物医学工程（可授...
- 105 篇 光学工程
- 89 篇 控制科学与工程
- 80 篇 电子科学与技术（可...
- 58 篇 仪器科学与技术
- 46 篇 机械工程
- 35 篇 化学工程与技术
- 27 篇 安全科学与工程
- 26 篇 交通运输工程
- 17 篇 动力工程及工程热...
423 篇 理学
- 189 篇 生物学
- 186 篇 数学
- 149 篇 物理学
- 76 篇 统计学（可授理学、...
- 54 篇 系统科学
- 40 篇 化学
165 篇 管理学
- 104 篇 图书情报与档案管...
- 69 篇 管理科学与工程(可...
- 37 篇 工商管理
145 篇 医学
- 129 篇 临床医学
- 87 篇 基础医学(可授医学...
- 65 篇 药学(可授医学、理...
- 23 篇 公共卫生与预防医...
28 篇 教育学
- 28 篇 教育学
27 篇 法学
- 21 篇 社会学
16 篇 经济学
16 篇 农学
5 篇 军事学
1 篇 文学
1 篇 历史学

主题

211 篇 machine learning
132 篇 deep learning
78 篇 signal processin...
72 篇 accuracy
71 篇 feature extracti...
68 篇 signal processin...
61 篇 support vector m...
57 篇 machine learning...
46 篇 predictive model...
33 篇 neural networks
32 篇 convolutional ne...
30 篇 random forests
29 篇 computational mo...
29 篇 training
26 篇 natural language...
26 篇 prediction algor...
21 篇 technological in...
20 篇 real-time system...
19 篇 adversarial mach...
18 篇 image processing

机构

16 篇 chitkara centre ...
14 篇 centre of resear...
12 篇 shenyang ligong ...
6 篇 ai & ds vishwaka...
6 篇 school of inform...
5 篇 department of me...
5 篇 khulna universit...
5 篇 department of co...
4 篇 delhi technologi...
4 篇 heilongjiang uni...
4 篇 department of s&...
4 篇 beijing univ pos...
4 篇 it vishwakarma i...
4 篇 department of co...
4 篇 sri lanka instit...
4 篇 advanced telecom...
4 篇 shenyang ligong ...
4 篇 graduate school ...
3 篇 chitkara univers...
3 篇 karunya institut...

作者

6 篇 mehta shiva
5 篇 rasmita panigrah...
4 篇 neelamadhab padh...
4 篇 wang xin
3 篇 m. vigenesh
3 篇 baydeti nagaraju
3 篇 sinambela marzuk...
3 篇 santosh kumar sh...
3 篇 ganapati panda
3 篇 debendra muduli
3 篇 abujar sheikh
3 篇 a. sivanantham
3 篇 li yajie
3 篇 li aihua
3 篇 zhou feng
3 篇 islam md. sanzid...
2 篇 aira kharvel par...
2 篇 nokshangthemba
2 篇 maheswara rao v ...
2 篇 lee tzong-ru

语言

1,292 篇 英文
32 篇 其他
11 篇 中文

检索条件"任意字段=Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning"

共 1333 条记录，以下是141-150 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：

Image Super Resolution using U-Net architecture and SRGAN: Comparative Analysis 2

Image Super Resolution using U-Net architecture and SRGAN: C...

引用

2nd international conference on Computer, Communication and Control, IC4 2024

作者： Dandekar, Pranali Bhojwani, Bhavika Balpande, Aarya Zanwar, Sanskar Deb, Ankan Shri Ramdeobaba College of Engineering and Management Department of Computer Science and Engineering [Artificial Intelligence and Machine Learning Nagpur India

ISBN: (纸本)9798350387933

Super-resolution is an important image processing task that improves the resolution of high-resolution images. Low resolution is used in many different fields, including medical imaging, satellite imagery, and computer vision. This paper presents a new approach to ultra-high resolution using the U-Net architecture, a deep learning framework known for its success in image segmentation and restoration *** this study, we propose an adaptive U-Net model specifically designed for ultra-high-resolution tasks. The architecture includes an encoder-decoder network with bypass connections, enabling multi-scale feature extraction and high-resolution detail reconstruction. Our model is trained on a diverse dataset of low- and high-resolution image pairs, allowing it to learn complex relationships and patterns in *** evaluate the performance of the U-Net based superresolution method using standard image quality metrics and qualitative visual evaluation. Test results show a significant improvement in image quality, with improved sharpness, texture, and detail recovery. Furthermore, our model outperforms state-of-the-art super-resolution methods in terms of signal-to-noise ratio (PSNR) and structural similarity index (SSIM). © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Low-voltage Topology Recognition Based on Carrier signal Injection 2

Low-voltage Topology Recognition Based on Carrier Signal Inj...

引用

2nd international conference on Image processing, Computer Vision and machine learning, ICICML 2023

作者： Zhang, Zhi Chen, Zhiru Zhao, Xi Du, Yan Shandong Jinan250002 China

ISBN: (纸本)9798350331417

Aiming at the problem of unclear low-voltage topology caused by the current low-voltage distribution network user information changes, meter fault replacement, station upgrades and other reasons, this paper designs a low-voltage topology identification method based on carrier signal injection. The method uses the signal generating device in the smart meter module to generate a carrier current signal with characteristic code bits in the power grid. According to the shunt characteristics of the current in the circuit, the branch carrier current signal of the injected carrier current signal has the greatest strength, and the other branch carrier current signals are much smaller than the injected signal branch. By comparing the strength of the carrier current signal to identify the low-voltage topology. Simulations and experiments show that this method can effectively identify low-voltage topology. © 2023 IEEE.

关键词： Carrier signal Carrier signal shunt FFT analysis User-transformer relationship recognition

来源：评论

学校读者我要写书评

暂无评论

An Efficient Selection Gate Logic Based Ripple Carry Adder for Deep learning Networks 2

An Efficient Selection Gate Logic Based Ripple Carry Adder f...

引用

2nd international conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Chetana, Lakshmi Naga B. Purna Sai Sandeep, C. Vasamth, K. Radha, S. Narasimhulu, C.V. Sai Krishna, K. Chaitanya Bharathi institute of Technology Department of ECE Hyderabad India

ISBN: (纸本)9798350366570

Full adders are fundamental components in digital circuit design, responsible for binary addition. Of late in Deep learning network architectures. Conventional full adder implementations often they are limited in terms of their speed, area, and power consumption. This study proposes a novel full adder architecture using multiplexers to overcome these challenges. This paper presents an enhanced VLSI (Very-Large-Scale Integration). A Ripple Carry Adder based multiplexer specially optimized for deep learning applications compared to traditional full Adder designs. Deep learning is a subset of artificial intelligence (AI) that teaches computers to mimic the human brain and process data. The introduction of this optimized RCA is expected to not only speed up the computation process but contributes to the overall efficiency of the deep learning network, making it more efficient in the design of the next Generation AI Processor. The proposed design utilizes a structured approach leveraging multiplexers to minimize delay and improve overall performance. The design is implemented as a ripple carry adder and extended to 64 bits to demonstrate scalability. The static analysis and simulation results up to 64-bit implementation reveal substantial reductions in delay, area, and power, making this design a highly efficient solution for modern high-speed digital systems. © 2024 IEEE.

关键词： Adders

来源：评论

学校读者我要写书评

暂无评论

A Deep learning Approach for Rectifying Fisheye Image 2

A Deep Learning Approach for Rectifying Fisheye Image

引用

2nd international conference on signal processing and Intelligent Computing, SPIC 2024

作者： Gai, Shuli Cui, Wenhua Liang, Bodong Tao, Ye University of Science and Technology Liaoning School of Computer and Information Engineering Anshan China Shenzhen Polytechnic University School of Automotive and Transportation Engineering Shenzhen China

ISBN: (纸本)9798350368888

Fisheye lens cameras offer a significantly wider field of view compared to conventional cameras. However, they also introduce geometric distortions and distorted shapes in captured images. This paper presents a self-supervised fisheye correction method based on convolutional neural networks. The method is trained using a readily available urban landscape roadway dataset and leverages the inherent stability of pixel coordinate relationships after uniform distortion to design an effective correction model. During the training process, distorted images are synthesized from the original undistorted images, and the predicted parameters are utilized to correct fisheye images. Furthermore, the loss function is constructed using the geometric mean of the Hough transform, and the entire model is trained with the assistance of the slope loss of the straight line, thus achieving an end-to-end framework. Experimental results demonstrate that our method provides superior performance in correcting real-world in-vehicle images, outperforming similar approaches in terms of correction accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

I- TVS: Instantaneous-Traffic Violation Surveillance System Using machine learning 2

I- TVS: Instantaneous-Traffic Violation Surveillance System ...

引用

2nd international conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Lokhande, Netra Ahirrao, Shripad Dhamale, Sharvari Shaikh, Moeez School of Electrical Engineering Dr. Vishwanath Karad MIT World Peace University Kothrud MS Pune411038 India

ISBN: (纸本)9798350305418

As the world rapidly modernizes, the progressive path lies in adopting smarter technologies for smart nations. In the present day, there is a widespread obsession with real-time information. Therefore, we propose an advanced system that utilizes AI and machine learning to provide timely violation data to offenders, including instances of signal jumping and riding a motorcycle without a helmet. Often, defaulters take the entire traffic system for granted, remaining unaware of their specific offenses. To achieve smarter cities, our plan involves installing intelligent traffic violation detection systems empowered by AI and machine learning. This innovative approach focuses on real-time violation tracking, & utilizing image processing to identify violators' vehicles’ registration plate. Additionally, it aims to publicly display these violations on billboards, showcasing the rider's image and the corresponding fine for greater awareness and deterrence. By doing so, we seek to raise awareness and significantly reduce traffic violations, thereby enhancing overall safety and compliance with traffic rules in urban areas. The integration of advanced technologies ensures greater accuracy and effectiveness in addressing traffic-related challenges. © 2023 IEEE.

关键词： accuracy machine learning smart cities smart technologies traffic violation detection system

来源：评论

学校读者我要写书评

暂无评论

Federated Deep learning for Multiclass Sentiment Analysis: Privacy-Preserving CNNs with Optimized Aggregation 2

Federated Deep Learning for Multiclass Sentiment Analysis: P...

引用

2nd international conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Mehta, Shiva Kumar, Ravi Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact & Outcome Punjab India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India

ISBN: (纸本)9798350366570

This research investigates an advanced sentiment classification model using Federated learning (FL) in conjunction with Convolutional Neural Networks (CNNs), concentrating on five sentiment categories: Very Negative, Negative, Neutral, Positive and Very Positive. This paper explores critical concerns about traditional centralized approaches, such as privacy, computational costs, and data heterogeneity. The federated learning-based model attained an average accuracy of 85.7% over five publicly accessible sentiment datasets. This paper's classification examples include IMDB Reviews, Yelp Reviews, news/reviews, Amazon Product Reviews, Twitter, Sentiment140, finance, and news. In this case, the highest classification accuracy was obtained at Amazon product reviews, which stood at 90.1 %. In comparison, the lowest average accuracy was obtained in Twitter Sentiment140 with an accuracy of 82.5 % due to large-scale social media data mess. To enhance the model's accuracy, we employed different aggregation algorithms, which showed an enhanced method known as Weighted Averaging as 3.4% better than the conventional FedAvg, particularly for datasets showing skewed classes. Additionally, performance improvement was observed, where clustered Aggregation increased performance by 2.7% on Yelp Reviews and Finance News Sentiment datasets. Also, the communication overhead was reduced in this work by reducing the communication frequency to every five rounds, which reduced the communication overhead by 15%. In contrast, the accuracy was only reduced by 0.5%. These results prove the effectiveness of the federated learning approach for both sentiment categorization and data privacy and computational and scenario efficiency. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Real- Time Compressed Domain Face Recognition Using Deep learning 2

Real- Time Compressed Domain Face Recognition Using Deep Lea...

引用

2nd international conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Senapati, Ranjan K Gondra, Indhu Panyala, Pragna Prasad, P.M.K. VNRVJIET Bachupally Dept of ECE Nizampet Hyderabad India GVPCE for Women Madhuravada Dept of ECE Andra Pradesh Vishakapatnam India

ISBN: (纸本)9798350366570

The growing demand for facial recognition systems necessitates efficient processing of images, particularly in resource-constrained environments. Compressed images offer a significant advantage in terms of storage and transmission bandwidth, but traditional face recognition algorithms struggle with the information loss inherent in compression techniques like JPEG. This paper explores the feasibility of using a VGG-16 based approach for real-time face recognition directly in the compressed domain. We leverage transfer learning by fine-tuning a pretrained VGG-16 model on a dataset of compressed facial images. This approach capitalizes on the powerful feature extraction capabilities of VGG-16 while adapting it to the challenges of compressed images, such as artifacts and information loss. Our evaluation demonstrates that the trained model achieves accurate face recognition using compressed images, paving the way for real-world applications with bandwidth and storage limitations. Future work could involve exploring the impact of different compression techniques on recognition accuracy and potentially improving robustness against compression artifacts. This work acknowledges the inherent tradeoff between the compression ratio of images and the achievable recognition accuracy. In this thesis, we are investigating this relationship to identify the optimal balance between storage efficiency and recognition performance for real-world deployments. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Classification of Hand Movements via EMG using machine learning Methods for Prosthesis 2

Classification of Hand Movements via EMG using Machine Learn...

引用

2nd international conference on Artificial Intelligence and signal processing, AISP 2022

作者： Karuna, M. Guntur, Sitaramanjaneya Reddy Department of Electronics and Communication Engineering Vignan’s Institute of Information Technology India Department of Biomedical Engineering Vignan’s Foundation for Science Technology and Research India

ISBN: (纸本)9781665442909

The recognition of hand movements using surface electromyography (sEMG) and a machine learning technique is becoming increasingly significant to control a prosthetic hand in a rehabilitation facility for people who have had their hands amputated in order to regain lost capability. However, in real life, controlling a prosthetic hand utilizing non-invasive methods is still a challenge. Existing research results are limited and not meeting the needs of amputee. The objective of this work is to fulfill the gap by proposing empirical mode decomposition (EMD) based machine learning (ML) classifier to recognize hand movements of the Ninapro dataset, this benchmark standard is used to evaluate four classifiers by comparing the performance accuracy results. The outcome of this work is better movement recognition achieved using one of the four distinct classifiers. © 2022 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A solar irradiance prediction method based on signal decomposition and Informer 2

A solar irradiance prediction method based on signal decompo...

引用

2nd international conference on Image processing, Computer Vision and machine learning, ICICML 2023

作者： Xu, Zhiwu Shanghai Maritime University Department of Electrical Engineering Shanghai200135 China

ISBN: (纸本)9798350331417

The historical data of solar irradiance are characterized by volatility and instability. These characteristics make it difficult to obtain satisfactory results when directly using prediction models to predict solar irradiance data. Therefore, this paper proposes a solar irradiance prediction model that combines signal decomposition methods and deep learning methods. First, feature selection is performed on the collected various meteorological characteristic data to determine the meteorological characteristics used for prediction. Secondly, in order to reduce the error in prediction results caused by the complexity of solar irradiance data, this method uses variational mode decomposition (VMD) to decompose the original data into multiple relatively stable subsequences. Thirdly, multiple sequences are predicted separately through the Informer model, and finally the prediction results are superimposed to obtain the final prediction value. Experiments show that the VMD-Informer model has higher accuracy in solar irradiance prediction than common deep learning models. © 2023 IEEE.

关键词： Deep learning Informer Solar irradiance prediction Variational modal decomposition

来源：评论

学校读者我要写书评

暂无评论

Underwater Image Restoration Based on Marine Snow Removal Techniques 2

Underwater Image Restoration Based on Marine Snow Removal Te...

引用

2nd international conference on signal processing and Intelligent Computing, SPIC 2024

作者： Li, Yiping Niu, Ben Zhou, Tianwei Gao, Hongwei Shenyang Ligong University School of Automation and Electrical Engineering Shenyang China Shenzhen University Greater Bay Area International Institute for Innovation Shenzhen China

ISBN: (纸本)9798350368888

Image capture and analysis in underwater environments have applications in many fields, such as underwater archaeological exploration, deep-sea biological research, oil and gas resource exploration, and path navigation of intelligent underwater robots. Existing underwater image restoration methods usually face problems such as high model complexity and the inability to be deployed on actual underwater operating platforms. This paper proposes an efficient and fast underwater image restoration method called UIRF-Net to address these issues. This method can restore underwater images and remove marine snow phenomena. UIRF-Net makes the deep learning network more lightweight by using modules such as channel extraction prior information and RGB three-channel color enhancement, improving the image color while ensuring the image quality and processing speed. Through experiments on the UIEB-Withsnow dataset, it is verified that UIRF-Net can produce clear underwater images from photos containing complex marine snow noise. This study provides a comprehensive enhancement solution for the field of underwater image restoration, which significantly improves the clarity of underwater photos. © 2024 IEEE.

关键词： Underwater photography

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134页 << < 11 12 13 14 15 16 17 18 19 20 > >>

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：