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4971-4980 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：

A BP neural Network-based Approach to Intelligent Computer image Recognition

A BP Neural Network-based Approach to Intelligent Computer I...

引用

Power Electronics, Computer applications (ICPECA), IEEE International conference on

作者： Jingwen Ze Tianjin University of Technology Tianjin China

The computer image recognition model based on BP neural network can effectively identify the convergence recognition error. To solve the problems of low convergence speed and inability to quickly reduce recognition errors in the practical application of traditional image recognition methods, an optimized model for computer image recognition based on GA & BP deep neural network algorithm is proposed through computer image data acquisition and processing, image recognition model construction based on BP neural network and computer image recognition model training.

关键词： Training image recognition Computational modeling neural networks Data models Real-time systems Power electronics

来源：评论

学校读者我要写书评

暂无评论

Learning Properties of Holomorphic neural networks of Dual Variables

Learning Properties of Holomorphic Neural Networks of Dual V...

引用

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

作者： Dmitry Kozlov Mikhail Bakulin Stanislav Pavlov Aleksandr Zuev Mariya Krylova Igor Kharchikov NN AI Team Huawei Russian Research Institute Nizhny Novgorod Russia Higher School of Economics National Research University Nizhny Novgorod Russia Volga State University of Water Transport Nizhny Novgorod Russia

artificial neural networks have become an inseparable element of human life. Researches do not stop at the current progress and try to improve neural networks and expand fields of applications. The most widespread way to make models better consists in generalization of existing methods and approaches. In this paper, we make a step in an unusual direction: we propose to use neural networks based on dual numbers. We develop a special subclass of dual-valued operators, which satisfy the equivalent of the Cauchy-Riemann equations for the dual domain. We also propose a new type of preprocessing and batch normalization, relying on peculiarities of dual numbers. We test deep holomorphic dual-valued models on music transcription and gravitational wave detection tasks and show that our holomorphic dual-valued networks achieve better inference time compared to the dual-valued models and are better than their real-valued counter-parts in sense of metrics.

关键词： Measurement Algebra Gravitational waves artificial neural networks Signal processing Mathematical models Hardware

来源：评论

学校读者我要写书评

暂无评论

Find and Dig: A Privacy-Preserving image processing Mechanism in Deep neural networks for Mobile Computation

Find and Dig: A Privacy-Preserving Image Processing Mechanis...

引用

International Joint conference on neural networks (IJCNN)

作者： Huang, Hongyu Zhao, Hongyuan Hu, Chunqiang Chen, Chao Li, Yantao Chongqing Univ Coll Comp Sci Chongqing Peoples R China Minist Educ Key Lab Dependable Serv Comp Cyber Phys Soc Chongqing Peoples R China Chongqing Univ Sch Big Data & Software Engn Chongqing Peoples R China

ISBN: (纸本)9780738133669

In recent years, there have been increasing demands for using deep neural networks (DNNs) to provide image processing services for mobile devices. Considering the privacy of users' images, we utilize a two-tiers DNN which deploys the shallow and deep model on mobile devices and the cloud respectively. Then we propose a novel privacy protection mechanism which is deployed on the mobile device to satisfy the differential privacy. Meanwhile, based on the convolution kernel analysis, we also propose a novel method to improve the computation efficiency of mobile devices. The highlight of our mechanism is that it not only provides customized privacy protection which can resist the attack of Generative Adversarial Network (GAN), but also improves the accuracy of the neural network model. The experimental results on the imageNet dataset show that we have improved the top-5 accuracy of image classification by 2%-3%. Under the premise of ensuring that the accuracy of the network is not degraded, our method reduces the CPU consumption on the VGG16 and ResNet50 networks to 74.6% and 48.9%, respectively, and can reduce 90% of the memory overhead. This improvement makes it possible to enable mobile deep neural network applications.

关键词： Deep Learning Differential Privacy image processing

来源：评论

学校读者我要写书评

暂无评论

Virtual Monitoring AI Robot Control System Based on Deep Learning

Virtual Monitoring AI Robot Control System Based on Deep Lea...

引用

Computer, Big Data and artificial Intelligence (ICCBD+AI), International conference on

作者： Li Tang School of Information Engineering Jingdezhen University Jingdezhen China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

With the continuous development of artificial Intelligence (AI) technology, especially the advancement of Deep Learning (DL), robotics has made significant breakthroughs, especially in the field of automatic monitoring and control. In this study, a virtual monitoring robot control system based on DL is designed and implemented, aiming to improve the robot's environmental adaptability and decision-making efficiency. In this study, a hybrid model combining Convolutional neural Network (CNN) and Recurrent neural Network (RNN) is used, which is capable of efficiently processing large amounts of dynamic data from robotic sensors. Firstly, it processes and parses image data through CNN for efficient recognition of static and dynamic objects in the environment; next, it processes time-series data using RNN in order to predict the possible behaviour and trajectories of the objects. In addition, this paper develops a real-time data processing framework that can continuously optimize the model parameters to adapt to real-time changes in the environment as the robot performs its tasks. The results of the study show that the success rate of tracking and monitoring in the morning is relatively high at all density levels. At low densities, the success rates fluctuated between 91% and 92.73%, indicating that the system performs consistently in the morning under low traffic volumes. In summary, this study not only demonstrates the effectiveness of DL technology in the field of virtual monitoring robotics, but also provides a valuable reference for the future direction of robotics.

关键词： Deep learning Adaptation models Recurrent neural networks Robot control Robot sensing systems Data models Real-time systems Convolutional neural networks artificial intelligence Monitoring

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Using CNN-LSTM and Vision Transformer 13th

Speech Emotion Recognition Using CNN-LSTM and Vision Transf...

引用

13th International conference on Innovations in Bio-Inspired Computing and applications, IBICA 2022, and 12th World Congress on Information and Communication Technologies, WICT 2022

作者： Kumar, C S Ayush Maharana, Advaith Das Krishnan, Srinath Murali Hanuma, Sannidhi Sri Sai Lal, G. Jyothish Ravi, Vinayakumar Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham Coimbatore India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia

ISBN: (纸本)9783031274985

The importance of speech emotion recognition has increased as a result of the acceptance of intelligent conversational assistant services. The communication between humans and machines may be made better via emotion recognition and analysis. We propose the application of attention based deep learning techniques to process and recognize speech emotions. In this paper we look at two major approaches CNN-LSTM and Mel Spectrogram-Vision Transformer based models and is compared over to the existing benchmarks. The experimental results roots for the feature extraction strategy of deep learning based approaches, eliminating the need of handpicking the features for traditional machine learning (ML) classifiers present in the current literature. A comparative study and evaluation between CNN-LSTM and Vision Transformers (ViT) have been evaluated and established from the experimental results. Both the models performed similarly with CNN-LSTM giving an accuracy of 88.50% when compared to the accuracy of 85.36% by ViT surpassing the existing benchmarks and providing the scope of study of attention and image processing based learning for speech emotion recognition. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Comparing MTCNN and Viola-Jones Algorithm in Face Recognition

Comparing MTCNN and Viola-Jones Algorithm in Face Recognitio...

引用

Iranian conference on Intelligent Systems (ICIS)

作者： Anahita Bahmeie Maryam Shakiba dept. Electrical Engineering Jundi-Shapur University of Technology Dezful Iran

ISBN: (数字)9798331507565

ISBN: (纸本)9798331507572

Taking into account the importance of human face recognition in numerous applications such as identity authentication, determining gender and age, analyzing facial expressions, assessing head pose, evaluating lighting conditions, and overcoming obstacles, the aim of this study is to investigate and contrast the effectiveness of neural networks and the Viola-Jones algorithm in recognizing human faces. To achieve this specific goal, the Multi-Task Cascade Convolutional neural Network (MTCNN) was used to evaluate the accuracy and processing time. In addition, the two algorithms MTCNN and Viola-Jones were compared in terms of accuracy and processing time. The results show that MTCNN can recognize the human face more accurately. At the same time, the processing time for face recognition with MTCNN is shorter than 71.63% compared to the processing time required by the Viola-Jones algorithm. The results clearly show that MTCNN works much faster, with a 71.63 % faster than the Viola-Jones algorithm.

关键词： Accuracy Head Face recognition image edge detection Lighting Authentication Multitasking Convolutional neural networks Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Agriculture through Leaf Disease Prediction in Plants

Revolutionizing Agriculture through Leaf Disease Prediction ...

引用

2023 IEEE Global conference on Information Technologies and Communications, GCITC 2023

作者： Anand, Sahana Shri Sankaran, Sariga Ravi, Sandhiya Hariharan, Shanmugasundaram Kukreja, Vinay Vasantha, S.V. Sri Sairam Engineering College Department of Information Technology Chennai India Vardhaman College of Engineering Department of Cse Hyderabad India Chitkara University Institute of Engineering and Technology Department of Computer Science and Engineering Punjab India

ISBN: (纸本)9798350308167

India's agricultural strength is hindered by plant diseases due to limited understanding of disease markers and remedies. Deep learning, particularly Convolutional neural networks (CNNs) and Recurrent neural networks (RNNs), offers hope for enhanced disease detection in agriculture. Our proposal centers on CNNs for accurate plant disease identification, streamlining the process. Urgency arises from economic repercussions and global food security. Deep learning is employed in various sectors such as healthcare, finance, and agriculture. Its applications range from identifying diseases, classifying weeds and leaves, to predicting soil moisture levels. The survey tackles current trends and objections in deep learning for plant disease prediction, guiding aspiring researchers. Machine Learning (ML) and Deep Learning (DL) tools replace costly visual inspection. Our study deploys ML algorithms including K Nearest Neighbors (KNN), Logistic Regression, Random Forest(RF) algorithm, Naïve Bayes, Decision Trees, and Support Vector Machines(SVM) on a diverse crop image dataset. A CNN-based system, coupled with ML soil analysis, suggests fitting crops, enabling informed planting choices. Classifier comparison validates Support Vector Classifier's (SVC) superiority. Swift disease detection is critical for food demand and economic growth. This study proposes a modern evaluation system using ML and pre-trained models (VGG16, InceptionV3, ResNet152) on datasets to classify plant diseases. IoT further augments disease and yield prediction, vital for modern agriculture. © 2023 IEEE.

关键词： artificial Intelligence(AI) CNN Deep learning Internet Of Things (IOT) KNN Logistic Regression Machine learning pre-trained models RF algorithm RNN SVM swift disease diagnosis

来源：评论

学校读者我要写书评

暂无评论

A loop closure detection method based on semantic segmentation and convolutional neural network 2

A loop closure detection method based on semantic segmentati...

引用

2nd International conference on artificial Intelligence and Electromechanical Automation, AIEA 2021

作者： Li, Hongyang Tian, Chengjun Wang, Lequan Lv, Hongfu Changchun University of Science and Technology Electronic Information Engineering Changchun China

ISBN: (纸本)9781665432658

As artificial intelligence flourishes and many related technologies continue to develop, Visual Simultaneous Localization and Mapping, as the 'vision' of robots, can utilize a large amount of environmental information. In addition, semantic segmentation can distinguish the background in the image from the moving objects. In recent years, convolutional neural networks have been successfully applied to image processing, and subsequently entered the field of V-SLAM research. Related researchers have tried to directly use convolutional neural networks to extract image features for loop closure detection, but the effect has not surpassed traditional methods. In order to make full use of image information, this paper proposes a loop closure detection and SLAM method based on semantic segmentation and convolutional neural network. © 2021 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A CNN-MLP hybrid architecture for visual model robustness

A CNN-MLP hybrid architecture for visual model robustness

引用

Computers and artificial Intelligence Technologies (CAIT), International conference on

作者： Hao Wang Chen Li School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China Shandong Hailiang Information Technology Institutes Jinan China

ISBN: (数字)9798331530891

ISBN: (纸本)9798331530907

In recent years, with the emergence of models based on Transformers and MLPs, such as Vision Transformer (ViT) and MLP-Mixer, researchers have begun to explore the potential of these new architectures in visual tasks. These models have achieved significant results, showing competitive performance compared to traditional CNNs. However, the robustness of models is another key research topic nowadays. To comprehensively evaluate the robustness of these models, researchers conducted extensive experiments on datasets including MNIST, Fashion-MNIST, and Fruit. Inspired by the above analysis, researchers proposed the MC (MLP-CNN) model, a hybrid architecture that combines the advantages of visual MLPs and convolutional neural networks. Experimental results show that the MC model demonstrated superior robustness across multiple datasets under adversarial attacks. These findings provide important references for designing more robust deep learning models and point the direction for future research in the field of image processing.

关键词： Deep learning Computers Visualization Computational modeling Computer architecture Transformers Feature extraction Robustness Convolutional neural networks artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Nutritional properties and quality assessment of breaded deep-frozen pollock fish cutlets using neural image analysis 13

Nutritional properties and quality assessment of breaded dee...

引用

13th International conference on Digital image processing (ICDIP)

作者： Duda, A. Duda, C. Szychta, M. Gierz, L. Przybyl, K. Koszela, K. Poznan Univ Life Sci Fac Food Sci & Nutr Dept Food Technol Plant Origin Wojska Polskiego 31 PL-60624 Poznan Poland Ind Inst Agr Engn Lukasiewicz Res Network Starolecka 31 PL-60963 Poznan Poland Poznan Univ Med Sci Fac Med Fredry 10 PL-61701 Poznan Poland Poznan Univ Life Sci Dept Biosyst Engn Wojska Polskiego 50 PL-60625 Poznan Poland Poznan Univ Tech Inst Machine Design Fac Mech Engn Piotrowo 3 PL-60965 Poznan Poland

ISBN: (数字)9781510646018

ISBN: (纸本)9781510646018

The aim of the research presented in this work was to develop a model of artificial neural networks (ANN) with the use of computer image analysis for the qualitative classification of deep-frozen raw material - breaded pollock cutlets (Backfisch). Shape and color discriminants were selected, by using a computer program, it was possible to obtain numerical data and build a learning set from them. This work is an example of using one of the methods of artificial intelligence in the food industry. The designed network was characterized by a very high ability for classification, its training was done by the technique of the so-called " with a teacher'. Such actions are motivated by the requirements of consumers who are becoming more and more attentive to the products they consume and expect calorically balanced and very high quality products.

关键词： artificial neural networks computer image analysis Pollock quality artificial intelligence

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：