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

18,869 篇 会议
1,421 篇 期刊文献
713 册 图书
59 篇 学位论文

馆藏范围

21,063 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

12,400 篇 工学
- 9,658 篇 计算机科学与技术...
- 4,668 篇 软件工程
- 3,236 篇 电气工程
- 2,913 篇 信息与通信工程
- 1,590 篇 生物工程
- 1,491 篇 控制科学与工程
- 1,212 篇 光学工程
- 1,145 篇 生物医学工程（可授...
- 722 篇 电子科学与技术（可...
- 562 篇 机械工程
- 450 篇 仪器科学与技术
- 302 篇 化学工程与技术
- 300 篇 材料科学与工程（可...
- 273 篇 网络空间安全
- 254 篇 安全科学与工程
- 230 篇 动力工程及工程热...
- 209 篇 交通运输工程
4,828 篇 理学
- 2,343 篇 物理学
- 1,768 篇 生物学
- 1,469 篇 数学
- 456 篇 统计学（可授理学、...
- 404 篇 化学
- 245 篇 系统科学
1,846 篇 医学
- 1,566 篇 临床医学
- 600 篇 基础医学(可授医学...
- 363 篇 药学(可授医学、理...
1,618 篇 管理学
- 986 篇 管理科学与工程(可...
- 727 篇 图书情报与档案管...
- 240 篇 工商管理
221 篇 农学
203 篇 教育学
- 197 篇 教育学
149 篇 法学
62 篇 经济学
48 篇 文学
25 篇 军事学
13 篇 艺术学
3 篇 哲学
2 篇 历史学

主题

3,539 篇 neural networks
2,904 篇 artificial neura...
2,498 篇 convolutional ne...
1,891 篇 deep learning
1,590 篇 feature extracti...
1,516 篇 image processing
1,441 篇 training
1,355 篇 artificial intel...
962 篇 accuracy
925 篇 image segmentati...
719 篇 machine learning
620 篇 deep neural netw...
604 篇 neurons
590 篇 computational mo...
461 篇 image recognitio...
460 篇 image classifica...
420 篇 computer archite...
418 篇 computer vision
404 篇 signal processin...
392 篇 object detection

机构

54 篇 chitkara univers...
27 篇 univ chinese aca...
23 篇 tsinghua univers...
20 篇 school of comput...
19 篇 university of el...
18 篇 university of sc...
18 篇 poznan univ life...
18 篇 university of ch...
17 篇 nanyang technolo...
16 篇 xidian univ sch ...
15 篇 school of comput...
15 篇 school of comput...
14 篇 hendisli&#x011f
14 篇 school of electr...
14 篇 shanghai jiao to...
14 篇 tsinghua univ pe...
13 篇 tongji universit...
12 篇 shanghai jiao to...
12 篇 lovely professio...
12 篇 the islamic univ...

作者

19 篇 de-shuang huang
16 篇 ryszard tadeusie...
16 篇 marcin korytkows...
15 篇 jacek m. zurada
11 篇 madani kurosh
11 篇 li yang
11 篇 liu yang
11 篇 liu ying
11 篇 ngoc thanh nguye...
10 篇 wang lei
10 篇 li xin
10 篇 wang jing
10 篇 jun wang
9 篇 haijun zhang
9 篇 gill kanwarparta...
9 篇 tianyong hao
9 篇 jun zhang
9 篇 li li
9 篇 shuzhi sam ge
9 篇 liu xin

语言

18,607 篇 英文
2,123 篇 其他
263 篇 中文
174 篇 土耳其文
7 篇 德文
4 篇 法文
3 篇 西班牙文
3 篇 俄文
2 篇 葡萄牙文
1 篇 日文

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

共 21063 条记录，以下是4921-4930 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：

HDR luminance normalization via contextual facilitation in highly recurrent neuromorphic spiking networks 24

HDR luminance normalization via contextual facilitation in h...

引用

conference on Unmanned Systems Technology XXIV

作者： White, Alexander J. Hung, Chou P. Lo, Chung-Chuan Natl Tsing Hua Univ Inst Syst Neurosci Hsinchu Taiwan DEVCOM Army Res Lab Aberdeen Proving Ground MD 21005 USA Natl Tsing Hua Univ Brain Res Ctr Hsinchu Taiwan

ISBN: (纸本)9781510651258;9781510651241

Previous research has shown that many luminance normalization mechanisms are engaged when viewing scenes with high dynamic range (HDR) luminance. In one such phenomenon, areas of similar luminance contextually facilitate the perception of ambiguous textures. Using inspiration from biological circuitry, we developed a recurrent spiking neural network that reproduces experimental results of contextual facilitation in HDR images. The network uses correlations between luminance and texture to correctly classify and segment ambiguous textures in images. While many deep neural networks can successfully perform many types of image analysis, they have limited ability to process images under naturalistic HDR illumination, requiring millions of neurons and power hungry GPUs. It is an open question if a recurrent spiking neural network can minimize the number of neurons required to perform HDR image segmentation based on texture. To that end, we designed a biologically inspired proof-of-concept recurrent SNN that can perform such a task. The network is implemented using leaky integrate-and-fire neurons, with CuBa synapses. We use the Nengo LOIHI API to simulate the network, so it can be run on Intel's LOIHI neuromorphic hardware. The network uses a highly recurrent structure to both group image elements based on luminance and texture, and to seamlessly combine these modalities to correctly segment ambiguous textures. Furthermore, we can continuously modulate how much luminance or texture contribute to the segmentation. We surmise that further development of this network will improve the resilience of optical flow computations under environments with complex naturalistic illumination.

关键词： Luminance texture neuromorphic artificial neural network contextual processing normalization

来源：评论

学校读者我要写书评

暂无评论

DATA-DRIVEN LOW-RANK neural NETWORK COMPRESSION

DATA-DRIVEN LOW-RANK NEURAL NETWORK COMPRESSION

引用

IEEE International conference on image processing (ICIP)

作者： Papadimitriou, Dimitris Jain, Swayambhoo Univ Calif Berkeley Berkeley CA 94720 USA InterDigital AI Lab Wilmington DE USA

ISBN: (纸本)9781665441155

Despite many modern applications of Deep neural networks (DNNs), the large number of parameters in the hidden layers makes them unattractive for deployment on devices with storage capacity constraints. In this paper we propose a Data-Driven Low-rank (DDLR) method to reduce the number of parameters of pretrained DNNs and expedite inference by imposing low-rank structure on the fully connected layers, while controlling for the overall accuracy and without requiring any retraining. We pose the problem as finding the lowest rank approximation of each fully connected layer with given performance guarantees and relax it to a tractable convex optimization problem. We show that it is possible to significantly reduce the number of parameters in common DNN architectures with only a small reduction in classification accuracy. We compare DDLR with Net-Trim, which is another data-driven DNN compression technique based on sparsity and show that DDLR consistently produces more compressed neural networks while maintaining higher accuracy.

关键词： Deep neural Network Compression Low-Rank Approximation Edge AI

来源：评论

学校读者我要写书评

暂无评论

Ensemble of CNN and DenseNet121 Models for Pneumonia Prediction Using X-Ray images 6

Ensemble of CNN and DenseNet121 Models for Pneumonia Predict...

引用

6th International conference on Contemporary Computing and Informatics, IC3I 2023

作者： Saxena, Suryansh Maji, Srabanti Agarwal, Aashray Goel, Anshul School of Computing DIT University Uttarakhand Dehradun India

ISBN: (纸本)9798350304480

When left untreated, pneumonia, a respiratory infection, can result in serious sickness or even death. In recent years, promising findings have been obtained in the accurate identification of pneumonia utilising X-ray image processing methods based on machine learning. In this article, we provide a deep learning-based approach for predicting pneumonia from X-ray images. We applied the averaging technique to combine CNN and DenseNet121, two well-known deep learning models, using a dataset from Kaggle. According to our tests, the CNN model had a test accuracy of 91.2% whereas DenseNet121 had an accuracy of 89.1%. The ensembled model's accuracy of 90.2 % shows how assembling can improve the accuracy of individual models. Our findings imply that deep learning models may prove to be a valuable tool for the precise and early detection of pneumonia, which may lead to better patient outcomes. © 2023 IEEE.

关键词： artificial intelligence CNN formatting insert Lung disease detection Machine learning neural networks Pneumonia detection using Machine Learning style styling

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Benefits of Knowledge Distillation against Adversarial Examples 6

Revisiting the Benefits of Knowledge Distillation against Ad...

引用

6th International conference on Data Science and Information Technology, DSIT 2023

作者： Li, Jiawen Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350304442

Deep neural networks (DNNs) have always been a popular base model in many image classification tasks. However, some recent works suggest that there are some man made images will easily lead DNNs give wrong predictions. These images are generated by adding some invisible perturbations into clean images, which are the so-called adversarial examples. Since they are almost similar to original data but can fool DNNs, adversarial examples can bring the insecurity to many life-critical applications. Adversarial knowledge distillation is a positive defense method to attach improved robustness to the target DNNs against adversarial examples. In distillation, student models are trained by soft labels coming from robust pre-trained teacher networks. However, it is hard for researchers to ensure that supervised information comes from a better teacher model. In this paper, We focus on four potential factors of the teacher that may have an effect to the distillation performance of student model, and investigate whether and when they can boost the model robustness against adversarial attacks. Multiple quantitative experiment illustrate that these factors have impact on the distillation process and these results can be considered to choose a better teacher model. Further studies can focus on the combination of adversarial knowledge distillation and other defense schemes. Empirical results in this paper may also help select proper teacher in new complex distillation tasks. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Real-Time Quality Inspection System Using Camera Vision and Machine Learning Algorithm: CNN

Real-Time Quality Inspection System Using Camera Vision and ...

引用

artificial Intelligence and Machine Learning applications Theme: Healthcare and Internet of Things (AIMLA), International conference on

作者： Shobana M Anushkumar S Arvinth Athikesav S E Harish R Suganth D Department of Computer Science and Business Systems M.Kumarasamy College of Engineering Karur India

ISBN: (数字)9798331538965

ISBN: (纸本)9798331538972

Guaranteeing product quality is an essential element of contemporary manufacturing, necessitating precise and effective inspection systems. This research introduces a real-time quality assessment system utilizing Convolutional neural networks (CNNs) to identify production flaws through high-resolution image data. The suggested system utilizes an improved Faster R-CNN model that boosts feature extraction, classification, and defect localization. The model undergoes training on a dataset containing six types of metal surface defects, attaining higher accuracy and computational efficiency than conventional machine vision methods. Experimental findings show that the enhanced Faster R-CNN reaches an accuracy of 98%, surpassing current methods like SVM and traditional CNNs. The results indicate that the suggested system can greatly enhance defect identification in industrial settings, minimizing manual inspection work and maintaining uniform product quality.

关键词： Support vector machines Accuracy Machine vision Production Inspection Feature extraction Real-time systems Product design Quality assessment Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Identification of Medicinal Plants for Medical Usage Using VGG16, ResNet50 and ResNet152

Identification of Medicinal Plants for Medical Usage Using V...

引用

Computer, Electronics & Electrical Engineering & their applications (IC2E3), International conference on

作者： Abhay Pandey Abhijeet Tripathi Anushka Aggarwal Meenakshi Yadav Department of Information Technology Galgotias College of Engineering & Technology Greater Noida UP India

ISBN: (数字)9798350388534

ISBN: (纸本)9798350388541

The suggested study describes how to identify therapeutic plants utilizing processing approaches. The precise identification of medicinal plants is critical. The healing nature of medicinal plants, in addition to their capacity for treat a variety of ailments, necessitate the requirement for automatic identification. Different plant portions, such as the root, fruit, bark, and stem, can help with identification; however, because leaf photographs are easily accessible and provide a wealth of information, they have been widely employed. This research studies the artificial intelligence field of deep learning and proposes an ensemble learning technique for swiftly recognizing medicinal plants from leaf photos. The suggested research only focuses on the identification and categorization of distinct leaf components in order to identify the plant species. The medicinal leaf dataset has thirty categories. The approach of transfer learning was employed in our work for initializing parameters the VGG 16, ResNet50, and ResNet152 neural networks. These component models were used with the SoftMax layer to extract attributes from the input photos. The accuracy of our model is 99 in comparison to MobileNetV2-Softmax Classification and InceptionV2-softmax classification (fivefold cross-validation) is 97.49 and 98.09 respectively.

关键词： Medicinal plants Accuracy neural networks Transfer learning Predictive models Ensemble learning Residual neural networks Biomedical imaging image classification Diseases

来源：评论

学校读者我要写书评

暂无评论

Identification of Non-Vaccinated People Using Face Recognition Based on CNN 1

Identification of Non-Vaccinated People Using Face Recogniti...

引用

1st International conference on Applied artificial Intelligence and Computing, ICAAIC 2022

作者： Kanimozhi, S. Arun, N. Singh, A.Madhan Kumar, S Shanthosh Tharanidharan, T. M. Kumarasamy College of Engineering Department of Information Technology Thalavapalayam Karur639113 India

ISBN: (纸本)9781665497107

Preventive medical care relies on vaccinations to provide significant health benefits. Vaccination is an important and effective preventive health measure. There is no better way to reduce the risk of pandemic spread of SARS-CoV-2/COVID-19 than vaccination. As a preventive measure, the government has begun vaccinating Indians against Corona infection. It is therefore important, in addition to developing and supplying vaccines, that enough people are willing to obtain vaccines. However, of the populations worldwide, there are concerning proportions that are reluctant to get vaccinated. In order to end the pandemic, it is highly essential to deal with another omnipresent issue: outright rejection of vaccinations. To achieve population immunity first we have to find the non-vaccinated population should be detected and to this end, this project proposed an Aadhaar-based facial recognition system is used to find non-vaccinated citizen and alert them using artificial Intelligence. Deep learning which is in the form of Convolutional neural networks (CNNs) are used to carry out the face recognition process and it is also proven to be an efficient method to carry out face recognition due to its high fidelity. A CNN is a Deep neural Network (DNN), which is designed to perform challenging tasks like image processing, which is crucial for facial recognition. The CNN structure is composed of numerous layers of neurons that connect the neurons: an input layer, an output layer, and layers between these two layers. In the midst of the epidemic coronavirus outbreak (COVID-19), a person's current inoculation status will be updated based on face recognition to safeguard him/her from COVID-19 and it may also serve as proof of vaccination for other purposes. Facial recognition technology (FRT) along with the Aadhaar helps to authenticate people before entering into any types of service. This project provides COVID-19 immunization status, which is determined by observing at their face, a

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on the Design of Financial Institution Customer Identity Verification Systems Based on artificial Intelligence and Machine Recognition

Research on the Design of Financial Institution Customer Ide...

引用

image processing and Computer applications (ICIPCA), IEEE International conference on

作者： Jiayi Shi Citibank (China) Co. Ltd. Shanghai China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

Over the recent years, fraudulent activities in financial institutions have increased in China; according to criminals, there are several approaches to deceiving their users. This article focuses on applying artificial Intelligence (AI) and Machine Learning in customer identity verification, a move driven towards recognizing and addressing the increasing bank fraud cases. The research introduces novel machine learning systems and models designed to determine fraudulent banking transactions. Various methods for enhancing detection accuracy are described. An artificial neural network-based model is proposed to enhance the system's efficiency and accuracy in identifying unauthorized transactions. The outcomes of variedly designed algorithms are, in this case, presented, typifying the impact of the logistic regression algorithm in enhancing the performance of the system, while stacked generalization demonstrates a higher AUC at 0.954. Recognizing bank fraud using artificial intelligence algorithms remains a significant concern in today's digital society.

关键词： Training Logistic regression Accuracy Machine learning algorithms Stacking Machine learning Banking Real-time systems Fraud Testing

来源：评论

学校读者我要写书评

暂无评论

A Brief Overview of Deep Learning based Techniques for the Detection of Wheat Leaf Disease: A Recent Study 7

A Brief Overview of Deep Learning based Techniques for the D...

引用

7th International conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Neog, Protyush Protim Batra, Salil Saraswat, Sudhir Sharma, Emani Likith Kumar, P. Pavan Pandey, Ankit Kumar Lovely Professional University Department of Computer Science and Engineering Punjab Phagwara India

ISBN: (纸本)9798350397253

Wheat is an important cereal crop and is the second most consumed cereal after rice globally. It is a staple food for more than one-third of the world's population. The production of wheat depends on various factors, such as climate, temperature, soil, pests, bacteria, and other biotic and abiotic factors. However, diseases can have a significant impact on wheat production. Various wheat diseases can affect crop yields,including leaf rust, leaf spot, spike infection, virus, bacterial back chaff, bacterial spike blight, and aphids. Leaf rust, in particular, is known to cause severe damage to wheat leaves. To combat these diseases, researchers have been investigating the use of advanced technologies such as deep learning and image-processing approaches for plant disease recognition. The process of disease detection involves several steps, including image preprocessing, segmentation, feature extraction, and classification. The accuracy of these steps directly affects the reliability and accuracy of the classification algorithms used to identify plant diseases. Recent studies have reviewed the state-of-the-art techniques used in this context and evaluated their effectiveness in real life applications. Overall, the use of advanced technologies such as deep learning and image processing for disease detection in wheat crops holds great promise in improving crop yields and reducing losses due to diseases. By identifying diseases at an early stage, farmers can take appropriate measures to control the spread of the disease and prevent significant crop damage. This research work presents a comparative analysis of the state-of-the-art work that has been carried out in this context and the effectiveness of the techniques in real-time. © 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

AttCDCNet: Attention-Enhanced Chest Disease Classification Using X-Ray images 22

AttCDCNet: Attention-Enhanced Chest Disease Classification U...

引用

22nd IEEE International Multi-conference on Systems, Signals and Devices, SSD 2025

作者： Khater, Omar H. Shuaibu, Abdullahi S. Haq, Sami Ul Siddiqui, Abdul Jabbar Computer Engineering Department Saudi Arabia SDAIA-KFUPM Joint Research Center for Artificial Intelligence KFUPM Computer Engineering Department Saudi Arabia

ISBN: (纸本)9798331542726

Chest X-rays (X-ray images) have been proven to be effective for the diagnosis of chest diseases, including Pneumonia, Lung Opacity, and COVID-19. However, relying on traditional medical methods for diagnosis from X-ray images is prone to delays and inaccuracies because the medical personnel who evaluate the X-ray images may have preconceived biases. For this reason, researchers have proposed the use of deep learning-based techniques to facilitate the diagnosis process. The preeminent method is the use of sophisticated Convolutional neural networks (CNNs). In this work, we introduce an innovative detection model named AttCDCNet for the task of X-ray image diagnosis, enhancing the popular DenseNet121 model by adding an attention block to help the model focus on the most relevant regions, utilizing the focal loss as a loss function to overcome the imbalance of the dataset problem, and utilizing depth-wise convolution to make the model lighter by reducing the parameters. The proposed model demonstrates novelty by effectively integrating these enhancements to address critical challenges in medical image classification, including dataset imbalance and computational efficiency. Through extensive experimental evaluations, the proposed model demonstrates exceptional performance, surpassing the original DenseNet121 and other state-of-the-art models. The proposed model achieved an accuracy, precision and recall of 94.94%, 95.14% and 94.53%, respectively, on the COVID-19 Radiography Dataset. Underscoring its potential to improve diagnostic accuracy and efficiency in real-world medical applications. © 2025 IEEE.

关键词： Chest Disease Classification Chest X-Ray Medical image Analysis

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 << < 489 490 491 492 493 494 495 496 497 498 > >>

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：