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

2,279 篇 会议
1,159 篇 期刊文献
255 册 图书
75 篇 学位论文
12 篇 科技报告

馆藏范围

3,780 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

2,501 篇 工学
- 1,858 篇 计算机科学与技术...
- 858 篇 软件工程
- 828 篇 电气工程
- 452 篇 信息与通信工程
- 280 篇 控制科学与工程
- 256 篇 光学工程
- 249 篇 生物工程
- 189 篇 生物医学工程（可授...
- 159 篇 电子科学与技术（可...
- 100 篇 材料科学与工程（可...
- 94 篇 仪器科学与技术
- 93 篇 机械工程
- 50 篇 化学工程与技术
- 47 篇 动力工程及工程热...
- 46 篇 测绘科学与技术
- 37 篇 网络空间安全
1,079 篇 理学
- 610 篇 物理学
- 308 篇 生物学
- 299 篇 数学
- 83 篇 化学
- 69 篇 统计学（可授理学、...
- 34 篇 地球物理学
- 33 篇 系统科学
422 篇 医学
- 321 篇 临床医学
- 160 篇 基础医学(可授医学...
- 59 篇 药学(可授医学、理...
303 篇 管理学
- 203 篇 管理科学与工程(可...
- 110 篇 图书情报与档案管...
- 39 篇 工商管理
63 篇 农学
- 44 篇 作物学
24 篇 法学
16 篇 教育学
9 篇 经济学
6 篇 文学
5 篇 艺术学
2 篇 哲学
2 篇 军事学
1 篇 历史学

主题

626 篇 neural networks
581 篇 artificial neura...
463 篇 artificial intel...
456 篇 image processing
395 篇 deep learning
379 篇 convolutional ne...
256 篇 feature extracti...
203 篇 machine learning
191 篇 training
156 篇 image segmentati...
154 篇 pattern recognit...
140 篇 computer vision
120 篇 image classifica...
118 篇 image recognitio...
116 篇 accuracy
110 篇 deep neural netw...
107 篇 neurons
96 篇 image processing...
95 篇 computational mo...
88 篇 neural network

机构

9 篇 chongqing univer...
9 篇 south china norm...
9 篇 harbin institute...
9 篇 univ chinese aca...
8 篇 northwestern uni...
7 篇 u.s. army resear...
7 篇 częstochowa univ...
6 篇 school of comput...
6 篇 univ shanghai sc...
6 篇 chitkara univers...
6 篇 hefei university...
6 篇 agh university o...
6 篇 information syst...
6 篇 tongji universit...
5 篇 technical univer...
5 篇 univ chinese aca...
5 篇 xidian univ sch ...
5 篇 univ shanghai sc...
5 篇 incept inst arti...
5 篇 university of wi...

作者

12 篇 nasrabadi nasser...
11 篇 de-shuang huang
10 篇 leszek rutkowski
9 篇 haijun zhang
9 篇 tianyong hao
9 篇 ryszard tadeusie...
9 篇 marcin korytkows...
9 篇 zhou wu
9 篇 lazaros iliadis
8 篇 jacek m. zurada
7 篇 gu min
7 篇 rafał scherer
7 篇 chrisina jayne
6 篇 a. rodriguez-vaz...
6 篇 zhai guangtao
6 篇 paolo masulli
6 篇 ilias maglogiann...
6 篇 rosenfeld a
6 篇 jagdish chand ba...
6 篇 shao ling

语言

3,505 篇 英文
149 篇 其他
104 篇 中文
21 篇 土耳其文
6 篇 德文
3 篇 法文
1 篇 西班牙文

检索条件"任意字段=Applications of Artificial Neural Networks in Image Processing VII"

共 3780 条记录，以下是701-710 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：

Improved image Classification with Manifold neural networks

Improved Image Classification with Manifold Neural Networks

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Caio F. Deberaldini Netto Zhiyang Wang Luana Ruiz Department of Applied Mathematics and Statistics Mathematical Institute for Data Science (MINDS) Data Science and Artificial Intelligence Institute (DSAI) Johns Hopkins University Baltimore USA Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph neural networks (GNNs) have gained popularity in various learning tasks, with successful applications in fields like molecular biology, transportation systems, and electrical grids. These fields naturally use graph data, benefiting from GNNs’ message-passing framework. However, the potential of GNNs in more general data representations, especially in the image domain, remains underexplored. Leveraging the manifold hypothesis, which posits that high-dimensional data lies in a low-dimensional manifold, we explore GNNs’ potential in this context. We construct an image manifold using variational autoencoders, then sample the manifold to generate graphs where each node is an image. This approach reduces data dimensionality while preserving geometric information. We then train a GNN to predict node labels corresponding to the image labels in the classification task, and leverage convergence of GNNs to manifold neural networks to analyze GNN generalization. Experiments on MNIST and CIFAR10 datasets demonstrate that GNNs generalize effectively to unseen graphs, achieving competitive accuracy in classification tasks.

关键词： Manifolds Electric potential High dimensional data Autoencoders Transportation Signal processing Graph neural networks Molecular biology Speech processing image classification

来源：评论

学校读者我要写书评

暂无评论

Automated Leukaemia Prediction and Classification Using Deep Learning Techniques 2

Automated Leukaemia Prediction and Classification Using Deep...

引用

2nd IEEE International Conference on Communication, Security and artificial Intelligence, ICCSAI 2023

作者： Narendran, M. Amarendra, K. Revathy, D. Divyapushpalakshmi, M. Sharma, Dilip Kumar Upreti, Kamal Kcg College of Technology Department of Information Technology Tamil Nadu Chennai India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522502 India Karpaga Vinayaga College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chengalpet India Gitam University Department of Computer Science and Engineering Bengaluru561203 India Jaypee University of Engineering and Technology Department of Mathematics Madhya Pradesh Guna473226 India Department of Computer Science Delhi -NCR Ghaziabad India

ISBN: (纸本)9798350369960

Leukemia is typically diagnosed based on an abnormal blood count, frequently an elevated White Blood Cell (WBC) count. The diagnosis is established through bone marrow, replaced by neoplastic cells. Acute Lymphoblastic Leukemia (ALL) is a type of leukaemia that affects the blood and bone marrow. Leukaemia primarily affects children and adults around the world. Early leukaemia detection is critical for appropriately treating patients, especially children. This research aims to present a diagnostic method that uses computational intelligence and image processing algorithms to identify blast cells from ALL images. The medical image is prepared initially using the preprocessing and segmentation technique for efficient classification. In this research, the type is accomplished using Bidirectional Associative Memory neural networks (BAMNN), where the accuracy is 96.87%, the highest classification rate and outperforms the existing technique. © 2023 IEEE.

关键词： accuracy activation function and associative memory bone marrow classification DL Leukaemia neural network neurons

来源：评论

学校读者我要写书评

暂无评论

Light weight encoder-decoder for underwater images in internet of underwater things (IoUT) 2

Light weight encoder-decoder for underwater images in intern...

引用

2nd International Conference on artificial Intelligence and Signal processing, AISP 2022

作者： Nair, Rashmi S. Agrawal, Rohit Domnic, S. Department of Computer Applications National Institute of Technology Tamil Nadu Tiruchirappalli India Department of Production Engineering National Institute of Technology Tamil Nadu Tiruchirappalli India

ISBN: (纸本)9781665442909

Internet of Underwater Things (IoUT) explores the applications of Internet of Things (IoT) to monitor the sea animal habitat, observe atmosphere, and predict defense and predict defense and disaster. Raw underwater images are affected by absorption and dispersal of light due to underwater environment. Low power computational devices are preferred to cut down the cost of IoUT devices. Because of underwater environment nature, transmission of underwater images captured by underwater devices is considered as a big challenge. There is a need to provide solutions to amplify color, contrast and brightness aspects of captured underwater images to provide good visual understanding. Conventional compression techniques used for terrestrial environment, causes ringing artefacts due to the variable characteristics of underwater images. Deep image compression techniques consume more computational power and time, making them least efficient for low power computational devices. In this study, a low computational power and less time-consuming image compression technique is proposed to achieve high encoding efficiency and good reconstruction quality of underwater images. The proposed technique suggests using Convolutional neural Network (CNN) at encoder side, which compresses and retains the structural data of the underwater image. And relative global histogram stretching based technique has been used at the decoder side to enhance the reconstructed underwater image. The proposed methodology is compared with conventional methods like Joint Pictures Experts Group (JPEG), Better Portable Graphics (BPG), Contrast Limited Adaptive Histogram Equalization (CLAHE) and deep learning techniques like Super Resolution Convolutional neural Network (SRCNN) and Residual encoder-decoder methods to evaluate the reconstructed image quality. The presented work provides high quality image in comparison with both conventional and SRCNN method. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of Efficient Multiply-Accumulate Unit for Convolutional neural networks 2

Design of Efficient Multiply-Accumulate Unit for Convolution...

引用

2nd International Conference on artificial Intelligence, Computational Electronics and Communication System, AICECS 2023

作者： Sajjan, Akash C Gadhave, Suyash Ratnakumar, Rahul Department of Electronics and Communication Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Convolutional neural networks (CNN) are used in a range of machine learning tasks, such as voice, image, and video processing. As the demand for faster response times in real-time applications grows, the need for high-speed implementation of CNNs is becoming more significant. However, the convolutional layer of CNNs is computationally demanding, leading to higher delays. Therefore, this study seeks to design an efficient and fast convolution block for the hardware implementation of the CNN algorithm. The proposed solution uses a Bit-Level Multiplier and Accumulator (BLMAC) unit that incorporates a modified Booth Encoder and Wallace Reduction Tree to achieve time optimization. The BLMAC, a key component of the convolution process, is optimized for speed. The area occupied by this architecture is 2761.517μm2, the power consumed is 121.4μW, and the delay is 9.11ns. Hence the proposed architecture is extremely power efficient and other parameters like area and delay have not been sacrificed to achieve this result. The proposed BLMAC architecture is designed using Verilog. The testbench for the code was verified and simulated in Cadence NCSIM. The synthesis is done in the Genus tool offered by Cadence. © Published under licence by IOP Publishing Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Advancing Age Estimation from Facial images Using Deep Learning Approaches and Ethical Considerations 2

Advancing Age Estimation from Facial Images Using Deep Learn...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Jayadharshini, P. Vasuki, C. Santhiya, S. Sudharshan, S. Sudheksha, K. Rithanya, M. Department of Artificial Intelligence Kongu Engineering College Tamilnadu Perundurai Erode India Department of Information Technology Nandha Engineering College Tamilnadu Erode India

ISBN: (纸本)9798331541217

Estimation of age from facial images is an important application in various fields, like biometrics, forensics, and personalized healthcare. The proposed work investigated the use of a machine learning approach to predict human age from facial features only, obtained from images. Our method used Convolutional neural networks (CNNs) in feature extraction and then combined regression models for age estimation. The used dataset is images of faces from different demographic groups, which makes the model robust and generalizable. All critical challenges related to variations in lighting, facial expression, and age distribution are adequately covered. The preprocessing steps, which include normalization and data augmentation, were properly applied to improve the performance of the models and reduce overfitting. Measures to report on prediction accuracy are also reported by using metrics such as Mean Absolute Deviation (MAD) and Root Mean Square Deviation (RMSD). The approach CNN-based shows a higher accuracy and computation rate compared to the baseline methods. Additionally, it presents practical applications of the models in missing people cases or for age-sensitive services. Ethical concerns such as privacy and control of bias are also of high concern and thus point to the need for clear and equitable use of such technology. This research seriously tests deep learning and shows its effectiveness in improving the estimation of age from facial images, providing important insights in relation to biometric solutions and more. © 2024 IEEE.

关键词： Age Estimation Convolutional neural networks (CNN) Facial Recognition image processing Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Synaptic turnover promotes efficient learning in bio-realistic spiking neural networks 57

Synaptic turnover promotes efficient learning in bio-realist...

引用

57th Asilomar Conference on Signals, Systems and Computers

作者： Malakasis, Nikos Chavlis, Spyridon Poirazi, Panayiota UoC Sch Med Iraklion Greece FORTH IMBB Iraklion Greece Tech Univ Munich Sch Life Sci Weihenstephan Munich Germany

ISBN: (纸本)9798350325744

While artificial machine learning systems achieve superhuman performance in tasks such as language processing and image/video recognition, they do so using extremely large datasets and consume huge amounts of power. On the other hand, the brain remains superior in several cognitively challenging tasks while operating with the energy of a small lightbulb. To explore how biology achieves such high efficiency, we built a biologically constrained spiking neural network model and assessed its learning capacity on various discrimination tasks. We found that a form of structural plasticity, namely the ability of synapses to form and eliminate continuously, results in higher performance accuracy and faster learning across all scenarios tested. These improvements are most significant under more difficult learning conditions, such as when the number of trainable parameters is halved or when the task difficulty is increased. The study highlights the important role of structural plasticity in optimizing learning in biological circuits and opens new avenues for exploring the applicability of such biological plasticity rules in machine learning applications.

关键词： dendrites spiking neural network structural plasticity synaptic turnover

来源：评论

学校读者我要写书评

暂无评论

BIBLIOMETRIC RESEARCH: TRACKING HOW THE artificial INTELLIGENCE INNTEGRATION CHANGED THE MEDICAL SYSTEMS

BIBLIOMETRIC RESEARCH: TRACKING HOW THE ARTIFICIAL INTELLIGE...

引用

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Kaur, Jasneet Kuamr, S. Barath Mehta, Pradnya Ninoria, Shalini Karthikeyan, C. Symbiosis College of Nursing Symbiosis International Deemed University Pune India Department of Biotechnology Karpagam Academy of Higher Education Coimbatore641021 India Vishwakarma Institute of Information Technology Pune India CCSIT TMU India School of Media Film&Television Studies IIMT University Meerut India Department of Computer Science Engineering Karpagam Institute of Technology Coimbatore641105 India

ISBN: (纸本)9798350355338

In latest generations, there has been a significant increase in study interest in the growing applications of artificial intelligence in health and medicine. The purpose of this study is to present a worldwide and chronological overview of AI study in the areas of medical care and health. The online science tool was used to obtain a total number of articles that were released between. The detailed study looked at the number of publications, as well as the cooperation between writers and nations. Generally, indicate that a factor, along with robotics, algorithms, neural networks, artificial cognitive computing, and natural language processing, were identified through a vast network of researchers' key words and phrases and message review of pertinent academic papers. These methods are regularly used in clinical forecasting and rehabilitation. The most articles were on cancer, followed by those on cardiovascular disease, stroke, blindness, Early onset dementia, and sadness. Additionally, the lack of study on applying AI to some illnesses with a high disease prevalence indicates potential paths for Ai development. The study proposes the creation of international and national guidelines and laws on the rationale and application of pertaining to medical products and provides a first and complete image of the global efforts made in this significant and lucrative study area. © 2024 IEEE.

关键词： Medical robotics

来源：评论

学校读者我要写书评

暂无评论

LoG-VMamba: Local-Global Vision Mamba for Medical image Segmentation 17th

LoG-VMamba: Local-Global Vision Mamba for Medical Image Seg...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Dang, Trung DQ. Nguyen, Huy Hoang Tiulpin, Aleksei University of Oulu Oulu Finland

ISBN: (纸本)9789819609000

Mamba, a State Space Model (SSM), has recently shown competitive performance to Convolutional neural networks (CNNs) and Transformers in Natural Language processing and general sequence modeling. Various attempts have been made to adapt Mamba to Computer Vision tasks, including medical image segmentation (MIS). Vision Mamba (VM)-based networks are particularly attractive due to their ability to achieve global receptive fields, similar to Vision Transformers, while also maintaining linear complexity in the number of tokens. However, the existing VM models still struggle to maintain both spatially local and global dependencies of tokens in high dimensional arrays due to their sequential nature. Employing multiple and/or complicated scanning strategies is computationally costly, which hinders applications of SSMs to high-dimensional 2D and 3D images that are common in MIS problems. In this work, we propose Local-Global Vision Mamba, LoG-VMamba, that explicitly enforces spatially adjacent tokens to remain nearby on the channel axis, and retains the global context in a compressed form. Our method allows the SSMs to access the local and global contexts even before reaching the last token while requiring only a simple scanning strategy. Our segmentation models are computationally efficient and substantially outperform both CNN and Transformers-based baselines on a diverse set of 2D and 3D MIS tasks. The implementation of LoG-VMamba is available at https://***/Oulu-IMEDS/LoG-VMamba. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

AI Based Automated Food Recognition Using CNN for Fitness Mobile Application

AI Based Automated Food Recognition Using CNN for Fitness Mo...

引用

2023 IEEE Symposium on Industrial Electronics and applications, ISIEA 2023

作者： Mahmood, Atif Mahmood, Rafay Azzuhri, Saaidal Razalli Azizul Hasan, Zati Hakim Mat Kiah, Miss Laiha University of Central Punjab Faculty of Information Technology and Computer Science Lahore Pakistan Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer System & Technology Kuala Lumpur50603 Malaysia Universiti Malaya Faculty of Computer Science and Information Technology Department of Artificial Intelligence Kuala Lumpur50603 Malaysia

ISBN: (纸本)9798350347494

Eating a healthy, balanced diet with regular exercise is important for maintaining physical and mental health. Healthy diet and exercise promise a healthier lifestyle. Other than that, people competing in different sports need a customized, strict workout and diet plan. Trainees offer their best at gymnasium by following a strict workout plan recommended by their coaches. However, there is no way till now to determine if the trainees are taking the prescribed diet strictly. Therefore, an optimized application with the feature of real time scanning of the prescribed meal can be helpful to overcome this problem. For this purpose, we have used Convolutional neural networks (CNN) along with image processing. Using ResNet50 with activation functions of ReLU and Softmax, our trained CNN model and the proposed architecture achieved an accuracy of 82.70 percent. We used CNN pre-trained models such as InceptionV3 with LeakyReLU and Softmax, InceptionV3 with ReLU and Softmax, VGG16 with ReLU and Softmax, VGG16 with ReLU and Softmax, and ResNet50 with ReLU and Softmax, so the achieved accuracy, respectively, is 78%, 71%, 58%, 56%, and 82.7%. Therefore, the proposed model has the potential to achieve high performance on real time food scanning which can be used in online fitness platforms(mobile applications and websites) and fitness gadgets. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Compact and Efficient neural networks for image Recognition Based on Learned 2D Separable Transform

Compact and Efficient Neural Networks for Image Recognition ...

引用

Digital Signal processing and its applications (DSPA), International Conference on

作者： Maxim Vashkevich Egor Krivalcevich Department of Computer Engineering Belarusian State University of Informatics and Radioelectronics Minsk Belarus

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

The paper presents a learned two-dimensional separable transform (LST) that can be considered as a new type of computational layer for constructing neural network (NN) architecture for image recognition tasks. The LST based on the idea of sharing the weights of one fullyconnected (FC) layer to process all rows of an image. After that, a second shared FC layer is used to process all columns of image representation obtained from the first layer. The use of LST layers in a NN architecture significantly reduces the number of model parameters compared to models that use stacked FC layers. We show that a NN-classifier based on a single LST layer followed by an FC layer achieves 98.02% accuracy on the MNIST dataset, while having only 9.5k parameters. We also implemented a LST-based classifier for handwritten digit recognition on the FPGA platform to demonstrate the efficiency of the suggested approach for designing a compact and high-performance implementation of NN models.

关键词： Accuracy image recognition Quantization (signal) Two-dimensional displays Transforms artificial neural networks Computer architecture image representation Field programmable gate arrays image classification

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378页 << < 67 68 69 70 71 72 73 74 75 76 > >>

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：