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

2,267 篇 会议
1,153 篇 期刊文献
254 册 图书
75 篇 学位论文
12 篇 科技报告

馆藏范围

3,761 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

2,484 篇 工学
- 1,851 篇 计算机科学与技术...
- 852 篇 软件工程
- 821 篇 电气工程
- 449 篇 信息与通信工程
- 277 篇 控制科学与工程
- 253 篇 光学工程
- 249 篇 生物工程
- 188 篇 生物医学工程（可授...
- 156 篇 电子科学与技术（可...
- 99 篇 材料科学与工程（可...
- 93 篇 机械工程
- 93 篇 仪器科学与技术
- 50 篇 化学工程与技术
- 46 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
- 34 篇 安全科学与工程
1,075 篇 理学
- 607 篇 物理学
- 307 篇 生物学
- 299 篇 数学
- 82 篇 化学
- 69 篇 统计学（可授理学、...
- 34 篇 地球物理学
420 篇 医学
- 319 篇 临床医学
- 160 篇 基础医学(可授医学...
- 59 篇 药学(可授医学、理...
302 篇 管理学
- 203 篇 管理科学与工程(可...
- 109 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
15 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

625 篇 neural networks
581 篇 artificial neura...
459 篇 artificial intel...
455 篇 image processing
393 篇 deep learning
371 篇 convolutional ne...
255 篇 feature extracti...
203 篇 machine learning
191 篇 training
155 篇 image segmentati...
154 篇 pattern recognit...
136 篇 computer vision
119 篇 image classifica...
118 篇 image recognitio...
115 篇 accuracy
107 篇 neurons
107 篇 deep neural netw...
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 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 chitkara univers...
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 rafał scherer
7 篇 chrisina jayne
6 篇 gu min
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

3,530 篇 英文
106 篇 其他
102 篇 中文
21 篇 土耳其文
5 篇 德文
2 篇 法文
1 篇 西班牙文
1 篇 朝鲜文

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

共 3761 条记录，以下是451-460 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 Survey on Adversarial Text Attacks on Deep Learning Models in Natural Language processing 5th

A Survey on Adversarial Text Attacks on Deep Learning Models...

引用

5th International Conference on Data Science, Machine Learning and applications

作者： Deepan, S. Torres-Cruz, Fred Placido-Lerma, Ruben L. Udhayakumar, R. Anuradha, S. Kapila, Dhiraj SR Univ Sch Comp Sci & Artificial Intelligence Warangal Telangana India Univ Nacl Altiplanode Puno Unit Stat & Comp Engn Puno Peru Univ Andina Nestor Caceres Velasquez Syst Engn Juliaca Peru VelTech Rangarajan Dr Sagunthala R&D Inst Sci & T Chennai Tamil Nadu India Sri Sairam Engn Coll Dept English Chennai Tamil Nadu India Lovely Profess Univ Dept Comp Sci & Engn Phagwara Punjab India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Deep neural networks have recently seen a significant surge in adoption for different artificial Intelligence technologies due to the development of powerful computer systems. However, because of the growing security concerns, they are susceptible to dangerous risks. Adversarial instances were initially discovered in the field of computer vision (CV), where systems were deceived by altering their initial inputs. In the field of natural language processing (NLP), additionally they occur. Several approaches are put up to address this gap and handle an extensive variety of NLP applications. We give an organized survey of these works in this *** text is distinct and meaningful in nature, in contrast to the image, which makes the creation of hostile assaults much more challenging. In this study, we present a thorough analysis of adversarial attacks and counterattacks in the textual domain. In order to make the essay self-contained, we examine related important works in computer vision and cover the fundamentals of NLP. We explore unresolved concerns to close the gap between current advancements and increasingly powerful adversarial assaults on NLP DNNs in our survey's conclusion.

关键词： NLP DNN adversarial text attacks adversarial defense textual data

来源：评论

学校读者我要写书评

暂无评论

Global Intelligent System for Waste Disposal Objects Monitoring Using the Discrete Orthogonal Transformations Based on neural Network Remote Sensing image processing 7

Global Intelligent System for Waste Disposal Objects Monitor...

引用

PROCEEDINGS OF SPIE Optics, Photonics and Digital Technologies for Imaging applications vii

作者： Kazaryan, M. Semenishchev, E. Voronin, V. North Ossetian State Med Acad Vladikavkaz Russia Moscow State Univ Technol STANKIN Ctr Cognit Technol & Machine Vis Moscow Russia

ISBN: (纸本)9781510651531;9781510651524

Remote sensing of the Earth allows to receive medium information, a high spatial resolution from space vehicles, and to conduct hyperspectral measurements. This study presents a remote sensing application using time-series Landsat satellite images to monitor the solid waste disposal site (WDS). The article proposes algorithms for working with spatial information, namely the transformation (convolution) of these manifolds into a one-dimensional sample. Recursive quasi-continuous sweeps are used for which the following conditions are satisfied: 1) preservation of the topological proximity of the original and expanded spaces, 2) preservation of correlations between the elements of the original and transformed spaces. An automated system is proposed for detecting and investigating waste objects based on the concept of fractal sets and convolutional neural networks. The first neural network detects WDS, the second works to localize the waste objects. This technique can become the object of further research on developing a medical-prophylactic expert system at the territorial level to detect and neutralize unauthorized waste disposal sites based on medium and high-resolution space images. As a result, the proposed method demonstrates good accuracy in detecting the solid waste disposal site on real satellite images.

关键词： waste disposal facility landfill waste degradation fractals discrete orthogonal transformations Fibonacci transforms image processing convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Expert System for Diagnosis of Cancer Diseases

An Expert System for Diagnosis of Cancer Diseases

引用

2024 International Conference on artificial Intelligence, Computer, Data Sciences, and applications, ACDSA 2024

作者： Madzinga, Christabel Mushiri, Tawanda Garikayi, Talon Mbohwa, Charles University of Zimbabwe Dept of Industrial and Mechatronics Engineering Harare Zimbabwe University of Zimbabwe Faculty of Medicine and Health Sciences Department of Biomedical Informatics and Biomedical Engineering Harare Zimbabwe Faculty of Health Sciences South Africa Harare Institute of Technology Harare Zimbabwe University of Johannesburg Dept of Quality and Operations Johannesburg South Africa

ISBN: (纸本)9798350394528

Traditional ways of diagnosing patients can take a lot of time and are sometimes undependable thus computerized technologies could be employed for more accurate and faster analysis. The third most diagnosed cancer in the world is a cancer called colorectal cancer (CRC). CRC results from unrestrained cell growth in sections of the large intestine, particularly the colon or rectum. Early diagnosis of CRC is important for the survival of the patient since it can result from changes in lifestyle and increase in age of the patient. The MATLAB image processing toolbox together with the QUPATH software was utilized for image preprocessing, segmentation and feature extraction. image were extracted for fine tuning the Visual Geometry Group-16 (VGG16) Convolutional neural Network (CNN), which was pretrained on the imageNet database thus enabling it to learn domain specific features necessary to classify the whole slide images. The concluding evaluation notes that the ground truth annotations are not ideal and thus the ability of deep learning to overcome issues in the quality of the data is verified. While due to the nature of the domain, deep learning techniques may never be suited to replace the expertise of practicing pathologists, they promise to aid in tasks which can be tedious, painstaking and subject to a degree of error and subjectivity." © 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

2nd International Conference on Big Data, Machine Learning, and applications, BigDML 2021

2nd International Conference on Big Data, Machine Learning, ...

引用

2nd International Conference on Big Data, Machine Learning, and applications, BigDML 2021

ISBN: (纸本)9789819934805

The proceedings contain 58 papers. The special focus in this conference is on Big Data, Machine Learning, and applications. The topics include: A Comparative Study of Loss Functions for Deep neural networks in Time Series Analysis;learning Algorithm for Threshold Softmax Layer to Handle Unknown Class Problem;traffic Monitoring and Violation Detection Using Deep Learning;conjugate Gradient Method for finding Optimal Parameters in Linear Regression;rugby Ball Detection, Tracking and Future Trajectory Prediction Algorithm;early Detection of Heart Disease Using Feature Selection and Classification Techniques;Gun Detection System for Surveillance Cameras Using HOG-Assisted KNN Classifier;Optimized Detection, Classification, and Tracking with YOLOV5, HSV Color Thresholding, and KCF Tracking;realtime Object Distance Measurement Using Stereo Vision image processing;COVID-19 Detection Using Chest X-ray images;Comparative Analysis of LDA Algorithm for Low Resource Indian Languages with Its Translated English Documents;text Style Transfer: A Comprehensive Study on Methodologies and Evaluation;classification of Hindustani Musical Ragas Using One-Dimensional Convolutional neural networks;w-Tree: A Concept Correlation Tree for Data Analysis and Annotations;crawl Smart: A Domain-Specific Crawler;evaluating the Effect of Leading Indicators in Customer Churn Prediction;classification of Skin Lesion Using image processing and ResNet50;data Collection and Pre-processing for Machine Learning-Based Student Dropout Prediction;Nested Named-Entity Recognition in Multilingual Code-Switched NLP;an Insight on Drone applications in Surveillance Domain;deep Learning-Based Semantic Segmentation of Blood Cells from Microscopic images;a Partitioned Task Offloading Approach for Privacy Preservation at Edge;artificial Intelligence in Radiological COVID-19 Detection: A State-of-the-Art Review.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BatchUp:A Feature Space-Level Multi-Data Mixing Technique for Convolutional neural Network 6

BatchUp:A Feature Space-Level Multi-Data Mixing Technique fo...

引用

6th International Conference on Next Generation Data-Driven networks, NGDN 2024

作者： Li, Rongxin Jilin University Artificial Intelligence Academy Changchun China

ISBN: (纸本)9798350388374

image data is a common data type in life, and the processing of massive image data has become a key factor in ensuring high-performance applications. However, researchers often face problems such as missing data and insufficient annotation when processing these data. In order to solve these problems, data enhancement technology emerged, which effectively expands the data set by transforming or synthesizing original images, providing more possibilities for model training. Among the existing data enhancement methods, they mainly include sample selection strategies and hybrid strategies. Among them, hybrid strategies are widely used, but sample selection strategies are rarely mentioned. This is because the sample selection process is full of unknowns, and it is easy to select mismatched features for mixing, causing the predicted values of the generated samples to be inconsistent with the original samples, making the generated samples become noise, thus degrading the predictive ability of the model. To overcome this challenge, this paper proposes a BatchUp hybrid approach. This method accurately selects and mixes the samples themselves. Since we mix some features in the hidden space, and the hidden space has more dimensional features, we will get more different samples, that is, we can have More information is used for training to ensure that the generated samples are consistent with the original samples in terms of predicted values. This not only solves the problems existing in current data augmentation technology, but also improves the prediction accuracy and generalization ability of the model. Experiments on CIFAR10/100, SVHN using ResNet architectures (including PreActResnet18/34 models) show that BatchUp improves or equals the current state-of-the-art CNN regularizer performance. © 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

Optimization of Convolution Operators' Backpropagation for Domestic Accelerators: Convolution Operators: Convolution kernel operation Backpropagation optimization to Enhance Performance and Efficiency in Convolutional neural Network 24

Optimization of Convolution Operators' Backpropagation for D...

引用

3rd International Conference on Computer, artificial Intelligence and Control Engineering, CAICE 2024

作者： Li, Wencong Chen, Yongqing Li, Bin School of Computing and Artificial Intelligence Zhengzhou University Zhengzhou China Co. Ltd Zhengzhou China

ISBN: (纸本)9798400716942

Since the emergence of Convolutional neural networks (CNNs), their special structure of weight sharing and high efficiency have found widespread applications in various fields such as speech recognition and image processing. To enhance computational efficiency and performance, convolutional operations are computed in parallel on domestic GPU-like accelerators, while CPUs are utilized for intricate logical decision-making or task scheduling. The paper focuses on an optimization method for backpropagation operators based on domestic GPU-like accelerators. By employing domestic GPU-like accelerators combined with the Implicit GEMM algorithm, it achieves universal operators, significantly reducing compilation time while maintaining performance without a substantial gap, thereby enhancing the efficiency and performance of CNN model training. The generic version of operators can substantially simplify the development and implementation process of CNN models. It possesses scalability and flexibility, catering to various application scenarios and requirements, enabling simultaneous processing of multiple data samples and computational tasks. Experimental results indicate that the efficiency of the generic version of operators meets expectations and can substitute for most operators in network training. © 2024 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

XAI-Based Feature Importance Analysis on Loop Optimization

XAI-Based Feature Importance Analysis on Loop Optimization

引用

1st International Conference on Smart Energy Systems and artificial Intelligence (SESAI)

作者： Katayama, Toshinobu Takahashi, Keichi Shimomura, Yoichi Takizawa, Hiroyuki Tohoku Univ Sch Engn Sendai Japan Tohoku Univ Cybersci Ctr Sendai Japan

ISBN: (纸本)9798350364613;9798350364606

In high-performance computing, performance tuning of a program is crucial and demanded in various situations. For instance, in image recognition applications using Deep neural networks (DNNs) such as autonomous driving, not only high accuracy but also high processing speed are required. Thus, Automatic Tuning (AT) has been attracting attention to automatically adjust the parameters of an application program that affect the program performance. In particular, in recent years, the utilization of AT leveraging Machine Learning (ML) models has been discussed. Although black-box models such as DNNs are adopted for advanced AT tasks, those models have highly complex structures, presenting challenges to humans in understanding how they are trained and how they make predictions. EXplainable artificial Intelligence (XAI) refers to a class of techniques that enable humans to understand how ML models are trained and how ML models make predictions. In this paper, AT with an ML model is first developed to optimize nested loops in DNN inference for image recognition. Then, the feature importance that the model has learned is quantified using Permutation Feature Importance (PFI), which is one of XAI. The quantification aims to reveal the underlying relationship between performance parameters and execution time learned by the model in a human-understandable form, thereby enhancing the interpretability of the model. Additionally, this paper investigates whether important features revealed by XAI align with the tuning results. The evaluation results show that features with significant importance, as elucidated by XAI, significantly influence the program performance. Accordingly, the results demonstrate that important features revealed by XAI align with the tuning results, underscoring the usefulness of employing XAI in AT.

关键词： Automatic Timing (AT) eXplainable artificial Intelligence (XAI) Interpretable Machine Learning Permutation Feature Importance (PFI) Feature Importance

来源：评论

学校读者我要写书评

暂无评论

Research on Segmentation of Intestinal Polyps Based on Improved Transformer and FCN 3

Research on Segmentation of Intestinal Polyps Based on Impro...

引用

3rd International Conference on artificial Intelligence, Big Data and Algorithms, CAIBDA 2023

作者： Chen, Xinjie Wang, Chen Wuhan Textile University WuHan430200 China

ISBN: (纸本)9781643684444

The rising prevalence of colon cancer necessitates early detection through colonoscopy. Deep learning segmentation technology has emerged as a reliable tool for detecting lesions, with convolutional neural networks (CNNs) leading advancements in medical image processing. However, manual polyp segmentation during colonoscopic examinations is time-consuming, highlighting the need for automated approaches. This study introduces a novel parallel branching structure to address limitations and improve contextual information and low-level detail handling. The structure extracts complementary features, enriching image analysis. Additionally, a quadratic complete volume integral branch enhances segmentation performance. We present our innovative model and methodology for polyp segmentation, advancing automated detection in colonoscopy. Experimental results demonstrate the effectiveness and robustness of our approach. By integrating deep learning techniques and leveraging our parallel branching structure, our method achieves superior segmentation accuracy for efficient and accurate polyp detection. © 2023 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Gender Recognition Based on Face image Using Deep Learning Method 11

Gender Recognition Based on Face Image Using Deep Learning M...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Wahyudi, Mochamad Bismi, Waeisul Firmansyah Raharjo, Mugi Rahardja, Untung Pujiastuti, Lise Universitas Bina Sarana Informatika Departement of Computer Science Jakarta Indonesia University Nusa Mandiri Departement of Informatics Jakarta Indonesia University Raharja Departement of Digital Business Tangerang Indonesia Stmik Antar Bangsa Departement of Information System Tangerang Indonesia

ISBN: (纸本)9798350305968

Gender recognition based on facial images is one of the interesting applications in the field of image processing and artificial intelligence. Deep Learning methods, particularly artificial neural networks, have emerged as an effective tool for extracting complex facial features and classifying gender with high accuracy. This research outlines a study that aims to develop an employee gender recognition system based on facial images using Deep Learning methods. The method used in this study proposes the inceptionV3 model as well as the OpenCV and matplotlib libraries in Python in involving the collection of facial image datasets covering different genders with a total of 1024 facial images, each with 40 attributes. This dataset was used to train a deep artificial neural network to recognize patterns and features that are unique to male and female genders and validated. Furthermore, the artificial neural network was tested with a dataset of never-before-seen facial images to evaluate the performance of the system. The results show that the InceptionV3 Deep Learning model has great potential in gender recognition based on facial images. The developed system was able to achieve a high level of accuracy in classifying the gender of individuals from facial images with a total accuracy of 94.8% against the test data, even in complex situations such as variations in facial expressions and lighting. © 2023 IEEE.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

image Schemas and image Schematic Complexes: Enhancing neural Machine Translation networks 1

引用

4th International Conference on Computational and Corpus-Based Phraseology (Europhras)

作者： Haddad, Amal Haddad Univ Granada Granada 18071 Spain

ISBN: (数字)9783031159251

ISBN: (纸本)9783031159251;9783031159244

Machine Translation (MT) is a Natural Language processing (NLP) application which has taken off and reported considerable progress in recent years. Most recent applications of MT employ neural networks imitating the principles of human understanding and creation of meaning at conceptual and cognitive levels (Nerlich and Clarke 2000: 141). They are based on techniques which try to simulate the mechanisms of learning in biological organisms carried out through the neurons (Aggarwal 2018: 1;Theordoris 2020: 903). However, human intelligence and the cognitive models which humans use through language should be subject to more examination in order to have the capacity to unveil more basic cognitive features. For this reason, a more holistic understanding of certain aspects of human intelligence based on cognitive models is still required in order to take machine learning a step further (Goertzel et al. 2012: 124). image schemas and image schematic complexes are among the cognitive issues which would benefit from further studies as its basic structure is fundamental in natural language processing and conceptualisation (Hedblom et al. 2019). They are common in all languages and all cultures but their use is not always universal. This variation influences the quality of MT, as in some cases, this variance is not taken into consideration while feeding the neural networks of MT. This preliminary study has the objective of studying the novel idea of image schemas and image schematic complexes and proposing an applied methodology to use them in MT.

关键词： image schemas Cognitive models Machine translation

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377页 << < 42 43 44 45 46 47 48 49 50 51 > >>

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：