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

6,021 篇 会议
130 册 图书
81 篇 期刊文献

馆藏范围

6,232 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,696 篇 工学
- 3,043 篇 计算机科学与技术...
- 1,548 篇 软件工程
- 967 篇 信息与通信工程
- 846 篇 电气工程
- 714 篇 生物工程
- 399 篇 控制科学与工程
- 399 篇 生物医学工程（可授...
- 398 篇 光学工程
- 147 篇 电子科学与技术（可...
- 136 篇 机械工程
- 112 篇 仪器科学与技术
- 112 篇 网络空间安全
- 108 篇 安全科学与工程
- 87 篇 化学工程与技术
- 77 篇 动力工程及工程热...
- 77 篇 交通运输工程
1,492 篇 理学
- 755 篇 生物学
- 664 篇 物理学
- 365 篇 数学
- 129 篇 统计学（可授理学、...
- 111 篇 化学
764 篇 医学
- 669 篇 临床医学
- 187 篇 基础医学(可授医学...
- 122 篇 药学(可授医学、理...
- 89 篇 特种医学
- 74 篇 公共卫生与预防医...
532 篇 管理学
- 292 篇 管理科学与工程(可...
- 283 篇 图书情报与档案管...
- 76 篇 工商管理
90 篇 农学
- 87 篇 作物学
55 篇 法学
36 篇 教育学
19 篇 经济学
12 篇 文学
9 篇 军事学
2 篇 艺术学
1 篇 哲学

主题

1,213 篇 convolutional ne...
1,161 篇 deep learning
912 篇 neural networks
665 篇 machine learning
628 篇 training
509 篇 feature extracti...
372 篇 accuracy
284 篇 computational mo...
257 篇 image processing
256 篇 image classifica...
254 篇 image segmentati...
230 篇 computer vision
218 篇 image recognitio...
194 篇 deep neural netw...
189 篇 visualization
174 篇 transfer learnin...
173 篇 artificial intel...
163 篇 computer archite...
162 篇 convolution
151 篇 support vector m...

机构

26 篇 chitkara univers...
10 篇 university of el...
9 篇 karnataka bangal...
9 篇 information syst...
9 篇 harbin institute...
8 篇 shanghai jiao to...
8 篇 school of comput...
8 篇 carnegie mellon ...
8 篇 school of comput...
7 篇 hefei university...
7 篇 south china norm...
7 篇 tongji universit...
7 篇 nanyang technolo...
7 篇 tech univ munich...
6 篇 chongqing univer...
6 篇 maharishi school...
6 篇 school of comput...
6 篇 univ chinese aca...
6 篇 king saud univer...
6 篇 department of co...

作者

14 篇 eyas el-qawasmeh
13 篇 de-shuang huang
8 篇 azizah abd manaf
7 篇 andrea vedaldi
7 篇 horst bischof
7 篇 mohana
7 篇 lazaros iliadis
7 篇 roy kaushik
7 篇 mukesh saraswat
6 篇 haijun zhang
6 篇 tianyong hao
6 篇 jan-michael frah...
6 篇 thomas brox
6 篇 amir h. gandomi
6 篇 zhou wu
6 篇 bilgin gokhan
6 篇 gokhan bilgin
6 篇 rueckert daniel
6 篇 liu chang
6 篇 zhao zhang

语言

5,191 篇 英文
985 篇 其他
74 篇 中文
34 篇 土耳其文
1 篇 日文
1 篇 俄文

检索条件"任意字段=Conference on Applications of Neural Networks and Machine Learning in Image Processing IX"

共 6232 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：

Volumetric Feature Extraction from 2D images Using Cubixels 23

Volumetric Feature Extraction from 2D Images Using Cubixels

引用

23rd IEEE International conference on machine learning and applications, ICMLA 2024

作者： Aburass, Sanad Rumman, Maha Abu Luther College Department of Computer Science DecorahIA United States Maharishi International University Department of Computer Science FairfieldIA United States

ISBN: (纸本)9798350374889

This paper introduces innovative volumetric feature extraction methods for 2D images using Cubixels and the Volume of the Void (VoV) metric. Cubixels transform traditional pixels into three-dimensional entities, capturing more detailed spatial and color relationships by assigning RGB values to the dimensions of width, length, and height. The VoV metric quantifies spatial gaps between adjacent Cubixels, providing valuable insights into textural characteristics and edge acuity. We developed two methods: the first focuses on calculating VoV between Cubixels, while the second integrates gradient and curvature features to enhance geometric feature extraction. These methods were applied to the CIFAR-10 and MNIST datasets and evaluated using four convolutional neural network (CNN) models incorporating residual connections, spatial dropout, and attention mechanisms. Our experimental results demonstrate significant improvements in model performance, including higher validation accuracy and reduced overfitting, as indicated by the Overfitting Index. This study underscores the potential of volumetric feature extraction in advancing image processing and computer vision, paving the way for more sophisticated and context-aware AI applications. © 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

Integrating the dynamic optimization strategies of Adam and AdaGrad 13

Integrating the dynamic optimization strategies of Adam and ...

引用

13th International conference on Intelligent Control and Information processing, ICICIP 2025

作者： Huang, Zhixuan Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9798331516147

Artificial intelligence (AI) has been a key research area since the 1950s, initially focused on using logic and reasoning to create systems that understand language, control robots, and offer expert advice. With the rise of big data and deep learning, AI has advanced in applications like recommendation systems, image recognition, and machine translation, primarily through optimizing loss functions in deep neural networks to improve accuracy and reduce training *** descent is the core optimization method but faces challenges like slow convergence and local minima. To overcome these, algorithms like Momentum, AdaGrad, RMSProp, Adadelta, Adam, and Nadam have been developed, introducing momentum and adaptive learning rates to accelerate convergence. This paper presents a new optimization algorithm that combines the strengths of Adam and AdaGrad, offering better adaptability to different learning rates. © 2025 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

BSMO: Enhancing Multitask learning Through Batch Swapping Optimization

BSMO: Enhancing Multitask Learning Through Batch Swapping Op...

引用

conference on Real-Time image processing and Deep learning

作者： Spencer, Zephaniah Schirner, Gunar Tabkhi, Hamed UNC Charlotte 9201 Univ City Blvd Charlotte NC 28223 USA Northeastern Univ 360 Huntington Ave Boston MA 02115 USA

ISBN: (纸本)9781510673878;9781510673861

With the advent of deep learning, there has been an ever-growing list of applications to which Deep Convolutional neural networks (DCNNs) can be applied. The field of Multi-Task learning (MTL) attempts to provide optimizations to many-task systems, improving performance by optimization algorithms and structural changes to these networks. However, we have found that current MTL optimization algorithms often impose burdensome computation overheads, require meticulously labeled datasets, and do not adapt to tasks with significantly different loss distributions. We propose a new MTL optimization algorithm: Batch Swapping with Multiple Optimizers (BSMO). We utilize single-task labeled data to train on a multi-task hard parameter sharing (HPS) network through swapping tasks at the batch level. This dramatically increases the flexibility and scalability of training on an HPS network by allowing for per-task datasets and augmentation pipelines. We demonstrate the efficacy of BSMO versus current SO TA algorithms by benchmarking across contemporary benchmarks & networks.

关键词： Deep learning Multi-Task learning Real-Time Vision

来源：评论

学校读者我要写书评

暂无评论

Utilising machine learning for Modulation and Signal processing 2

Utilising Machine Learning for Modulation and Signal Process...

引用

2nd IEEE World conference on Communication and Computing (WCONF)

作者： Singh, Daljeet Pal Solanki, Madhav Singh Jyothi, Renuka S. Maharishi Univ Informat Technol Maharishi Sch Engn & Technol Uttar Pradesh India Sanskriti Univ Dept Comp Sci & Engn Uttar Pradesh India Jain Deemed Be Univ Dept Biotechnol & Genet Sch Sci Bangalore Karnataka India

ISBN: (纸本)9798350395334;9798350395327

Device studying (ML) is an effective device that has been used in many packages, consisting of virtual sign processing, communications structures, and modulation reputation. In particular, ML has been extensively studied for modulation recognition, which is a hard hassle because of the always-changing and unpredictable nature of the sign. With the aid of leveraging ML strategies, which can be used to quantify and check specific houses of a signal, reliable modulation popularity and signal processing strategies can be evolved. For instance, ML can be used to automatically discover modulation class when the image shape of the signal is unknown. It is achieved via reading the sign with device learning techniques consisting of Fourier transform;waveletbased totally function extraction, and convolutional neural networks. Different applications encompass channel estimation, signal detection, and optimization of verbal exchange networks. Further to recognizing modulation codecs, ML-based algorithms may be used to enhance signal processing and communique systems. It could be done with the aid of developing smarter systems that are capable of studying global data. ML can be used to robotically apprehend anomalous alerts and allow networks to quickly adapt to converting situations. ML techniques can also be used to optimize community parameters, which include power management, coding schemes, and modulation codecs, so as to maximize their performance.

关键词： Consisting Communications Modulation Techniques Parameters Management

来源：评论

学校读者我要写书评

暂无评论

Deep learning for Sentiment Analysis with Adaptive neural networks for Emotion Classification 5

Deep Learning for Sentiment Analysis with Adaptive Neural Ne...

引用

5th International conference on Sustainable Communication networks and Application, ICSCNA 2024

作者： Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Deepa, R. Surendran, R. SRM Institute of Science and Technology Department of Computer Science and Applications Tamilnadu Chennai India Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM institute of Science and Technology Department of Computing Technologies Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

In understanding human emotions, sentiment analysis has been invaluable in social media monitoring, consumer comment analysis, and psychological evaluations. Customer service, human-computer interface, and public mood comprehension depend on appropriate emotion categorisation. Despite its potential, sentiment analysis struggles with sarcasm, multimodal data integration, and emotion processing. Implementing real-time applications requires improving deep learning model computational complexity. Multimodal Optimised Emotion Analysis using Deep learning (MOEA-DL) uses CNNs for image processing, RNNs for text., and LSTM networks for sequential audio data. This improves emotion recognition by combining modality strengths. Marketing sentiment, mental health monitoring, social media sentiment, and consumer feedback use MOEA-DL. Multimodal solutions are better than text-based ones for communicating emotion. Customer contacts, film reviews, and social media platforms are used to evaluate the proposed strategy. According to simulations, MOEA-DL categorises emotions more accurately and robustly than previous sentiment analysis methods. Its adaptive neural network lets the system learn and perform well in many cultural and language environments. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Characteristics of Gradient Descent and Non-Gradient Descent-Based Algorithms in neural Network learning 4

Analyzing the Characteristics of Gradient Descent and Non-Gr...

引用

4th IEEE International conference on Electrical, Computer, and Energy Technologies, ICECET 2024

作者： Kim, HyunJung Konkuk University dept. of SANG-HUH COLLEGE Seoul Korea Republic of

ISBN: (纸本)9798350395914

In this paper, a comparative analysis of optimization algorithms for artificial neural networks widely used in the fields of machine learning and deep learning was conducted. Beyond the conventional backpropagation algorithm utilizing gradient descent, we investigated the characteristics of various optimization methods for neural networks, including alternative non-gradient descent approaches such as the Forward-Forward (FF) algorithm and Genetic Algorithm (GA). Our analysis revealed diverse performances of each algorithm contingent upon the characteristics of the image dataset and the problem at hand. Furthermore, by scrutinizing the features and limitations of each algorithm, we provided considerations for practical applications. These findings offer crucial guidelines for selecting the optimal weight update methods tailored to specific problem domains. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Text Extraction from Document images using CNN and LSTM

Text Extraction from Document Images using CNN and LSTM

引用

2023 International conference on Sustainable Communication networks and Application, ICSCNA 2023

作者： Shinde, Sandip Bhosle, Sanket Bomble, Gaurav Bhosale, Shourya Bokil, Siddhant Vishwakarma Institute of Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350313987

This research study proposes an advanced system that combines image processing techniques with deep learning models to achieve precise text extraction from images. Our approach in this paper involves several key steps. First, we apply preprocessing techniques to enhance the image quality and clarity of text regions. Next, the proposed method employs image processing algorithms to identify and isolate text regions within the image. To recognize and transcribe the extracted text, the proposed method utilizes deep learning models, specifically convolutional neural networks (CNNs) and recurrent neural networks (RNNs). To train the deep learning model in the proposed method, we generate a labeled dataset by annotating text regions in images. The proposed model highlights the effectiveness of integrating image processing and deep learning techniques in achieving accurate and efficient text extraction from images. The system's performance and flexibility make it a valuable tool for applications that require reliable text extraction capabilities. © 2023 IEEE.

关键词： activation function Convolutional neural Network (CNN) deep learning Recurrent neural Network (RNN) text extraction from images

来源：评论

学校读者我要写书评

暂无评论

Digital Media Art Style Conversion Algorithm Based on Deep neural Network 5

Digital Media Art Style Conversion Algorithm Based on Deep N...

引用

5th International conference on machine learning and Big Data Analytics for IoT Security and Privacy, SPIoT 2024

作者： Zhao, Shen College of Art and Design Xi'An Fanyi University Shaanxi Xi'an710105 China

With the rapid development of digital media art, artistic style transfer technology has gradually become a hot research field. However, existing style transfer methods often face the problems of information loss and insufficient style consistency when processing complex images, which limits their effectiveness and flexibility in practical applications. In this paper, a deep neural network-based style transfer algorithm is proposed for digital media arts towards improving quality and accuracy in style transfer. Starting from a deep neural network model, a multi-level feature extraction and reconstruction strategy is adopted, with the source image and the target style image jointly trained to achieve more efficient style fusion. The perceptual loss function was introduced to optimize the quality of the generated image. It underwent rigorous testing and evaluation on multiple public datasets. The style transfer algorithm based on deep neural networks is therefore able to boost artistic expression while conserving high-quality content and style consistency. This is a creation that envisions fresh technical means and approaches for creative digital media art. © 2025 The Authors. Published by Elsevier B.V.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

neural networks and Their applications in Smart Systems 9th

Neural Networks and Their Applications in Smart Systems

引用

9th International conference on Smart City applications, SCA 2024

作者： Atmani, Aziz Boumhamdi, Mounir Laboratoire de Recherche Business Intelligence Gouvernance des Organisations Finance et Criminalité Financière Université Hassan II Faculté des Sciences Juridiques Économiques et Sociales de Casablanca No8110 Oasis Casablanca Morocco

ISBN: (纸本)9783031886522

This work investigates the potential of neural networks in the processing of artificial intelligence, especially in smart systems, and explores their applications regarding advancing automation, user experience, and resource management. The methodology will include collecting data from public datasets and international organizations, preprocessing or cleaning, normalization and augmentation of data, followed by the development of different neural network models: Convolutional neural networks for image recognition;Recurrent neural networks and Long Short-Term Memory for speech recognition and time series prediction;hybrids for such complicated tasks as energy consumption forecasting andhealth data analysis. Results are very high for a wide variety of datasets, with CNNs attaining state-of-the-art in image recognition, LSTMs doing the same in speech recognition with very low word error rates, and the hybrids quite effective in predictive analytics and health data analysis. The discussion has been about how neural networks are impacting smart systems in a big way while also presenting the challenges regarding the requirements around data and computational resources and model interpretability. Future directions in this regard may include transfer learning, explainable AI, edge computing, and quantum computing to further enhance neural network capabilities. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Kidney Diseases Using Deep learning: A Comparative Analysis with machine learning Models on CT images

Automated Classification of Kidney Diseases Using Deep Learn...

引用

2024 International conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024

作者： Jain, Eshika Kukreja, Vinay Kaushik, Pratham Aneja, Aseem Chitkara University Institute of Engineering and Technology Centre for Research Impact & Outcome Punjab Rajpura140401 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India

ISBN: (纸本)9798350369175

Kidney disease diagnosis with the use of a medical image plays an important role in diagnosis and treatment on time. This survey presents a comparison between different machine learning algorithms and deep learning models that classify kidney conditions from the CT KIDNEY DATASET, containing four distinct classes: Normal, Cyst, Tumor, and Stone. The authors have reviewed the performance of CNNs while comparing them against traditional machine learning models like Decision Trees, Random Forests, Gradient Boosting, AdaBoost, Support Vector Classifiers (SVC), Logistic Regression, K-Neighbors, Naive Bayes, and Long Short-Term Memory (LSTM) networks. The best performance, by the CNN model, is 93.87%, which states the power of deep learning in image processing regarding medical applications. In contrast, Random Forest and Decision Tree models remain competitive within traditional classifiers with validation accuracies of 83.37% and 83.05%, respectively. Gradient Boosting, AdaBoost, and SVC models come next with validation accuracies ranging from 82.73% to 79.60%, whereas KNeighbors and Naive Bayes are still farther behind, although each was performing consistently. It reflects the particular challenges associated with the application of recurrent models to static image data, best suited for temporal data. Our LSTM model realizes a test accuracy of $\mathbf{75.18 \%}$. It also points to the fact that CNNs exhibit a far better capability in detecting kidney diseases, whereas traditional models are quite viable alternatives with competitive accuracy. In fact, this essentially points out that model selection is an important issue in clinical applications, as accuracy and computational efficiency go hand in hand to enable accurate diagnosis. © 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

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 << < 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：