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

2,392 篇 会议
167 册 图书
76 篇 期刊文献
3 篇 学位论文

馆藏范围

2,638 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,659 篇 工学
- 1,318 篇 计算机科学与技术...
- 531 篇 软件工程
- 438 篇 电气工程
- 319 篇 信息与通信工程
- 169 篇 生物工程
- 158 篇 控制科学与工程
- 151 篇 光学工程
- 135 篇 生物医学工程（可授...
- 81 篇 电子科学与技术（可...
- 60 篇 机械工程
- 57 篇 仪器科学与技术
- 33 篇 网络空间安全
- 26 篇 材料科学与工程（可...
- 25 篇 动力工程及工程热...
- 25 篇 化学工程与技术
- 25 篇 安全科学与工程
699 篇 理学
- 446 篇 物理学
- 185 篇 生物学
- 160 篇 数学
- 38 篇 化学
- 36 篇 统计学（可授理学、...
- 22 篇 系统科学
251 篇 医学
- 219 篇 临床医学
- 77 篇 基础医学(可授医学...
- 45 篇 药学(可授医学、理...
- 28 篇 公共卫生与预防医...
172 篇 管理学
- 104 篇 管理科学与工程(可...
- 75 篇 图书情报与档案管...
- 28 篇 工商管理
27 篇 农学
- 27 篇 作物学
22 篇 法学
15 篇 教育学
6 篇 经济学
6 篇 文学
1 篇 哲学
1 篇 军事学

主题

391 篇 artificial neura...
381 篇 neural networks
278 篇 convolutional ne...
260 篇 image processing
247 篇 artificial intel...
216 篇 deep learning
190 篇 feature extracti...
149 篇 training
114 篇 image segmentati...
105 篇 accuracy
104 篇 pattern recognit...
94 篇 machine learning
91 篇 image classifica...
83 篇 image recognitio...
79 篇 computer vision
75 篇 neurons
75 篇 computational mo...
72 篇 neural network
61 篇 information syst...
60 篇 image processing...

机构

7 篇 częstochowa univ...
6 篇 chongqing univer...
6 篇 king saud univer...
6 篇 hefei university...
6 篇 agh university o...
6 篇 information syst...
6 篇 south china norm...
6 篇 harbin institute...
5 篇 lovely professio...
5 篇 university of ca...
5 篇 chitkara univers...
5 篇 democritus unive...
5 篇 department of ma...
4 篇 school of comput...
4 篇 department of ma...
4 篇 univ chinese aca...
4 篇 razak faculty of...
4 篇 department of ma...
4 篇 department of co...
4 篇 tongji universit...

作者

12 篇 eyas el-qawasmeh
9 篇 de-shuang huang
9 篇 ryszard tadeusie...
9 篇 marcin korytkows...
9 篇 leszek rutkowski
8 篇 jacek m. zurada
8 篇 azizah abd manaf
8 篇 lazaros iliadis
7 篇 rafał scherer
7 篇 lopez-rubio ezeq...
6 篇 haijun zhang
6 篇 tianyong hao
6 篇 jagdish chand ba...
6 篇 zhou wu
6 篇 kedar nath das
6 篇 zhao zhang
6 篇 gelenbe e
6 篇 kusum deep
5 篇 włodzisław duch
5 篇 duoqian miao

语言

2,544 篇 英文
58 篇 其他
23 篇 中文
22 篇 土耳其文
1 篇 西班牙文

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

共 2638 条记录，以下是2311-2320 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 Dynamic Analysis of a Dual Memristive Hopfield neural Network

A Dynamic Analysis of a Dual Memristive Hopfield Neural Netw...

引用

neural networks, Information and Communication Engineering (NNICE), International conference on

作者： Na Li Zhaoxing Wang Lili Huang School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China Collaborative Innovation Center of Memristive Computing Application (CICCA) Qilu Institute of Technology Jinan China

The human brain, as a large and highly complex nonlinear dynamical system, has a close connection with human intelligence activities. The artificial neural network based on memristors has shown excellent performance in simulating the working mechanism of the human brain. Therefore, in the HNN neural network, both hyperbolic tangent memristors and quadratic nonlinear memristors are introduced to couple with it. Using basic dynamical analysis methods, the paper discusses the dynamical behavior of the system under different coupling strengths and studies the behavior of attractor symmetry under different initial values. The experimental results show that under different memristor parameters, by observing the changes in the phase trajectory diagram, Lyapunov exponent, and bifurcation diagram of the system, it is found that it has periodic doubling bifurcation, chaos, periodic window, and double vortex attractor symmetry behavior. At the same time, it also emphasizes its full sensitivity to initial values. At the same time, its complex dynamical characteristics also provide research support for applications in data processing, image encryption, biomedical, and other fields.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Household Waste Classification Algorithms Based on Various Convolutional neural networks: A Review of Performance Optimization

Household Waste Classification Algorithms Based on Various C...

引用

International conference on Wavelet Active Media Technology and Information processing (ICWAMTIP)

作者： Huang Renxiang Chen Jia Li Jianping School of Artificial Intelligence and Big Data Sichuan University of Arts and Science Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

This paper reviews the research progress of deep learning-based household waste classification algorithms. It first introduces the importance of household waste classification and the application value of deep learning in this field. Next, it outlines the theoretical foundations of deep learning technology in waste classification, including the principles of convolutional neural networks and their applications in image recognition. The article provides a detailed analysis of the application of different deep learning models in waste classification, such as MobileNetV2, ShuffleNetV1, EfficientNetV1, and YOLOV5, as well as their optimizations and innovations in practical applications. Furthermore, it discusses optimization and innovation methods for deep learning models, including learning rate adjustment, optimizer selection, attention mechanisms, data augmentation, and lightweight network design. Finally, it summarizes the current research shortcomings and challenges, and looks forward to future research directions. This review provides a systematic perspective for a deeper understanding of the application of deep learning in waste classification and offers directions for future research.

关键词： Deep learning Analytical models Technological innovation Attention mechanisms Reviews Data augmentation Data models Classification algorithms Convolutional neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

Transformation Parameters Estimation for Medical image Registration Using CEL-DNN

Transformation Parameters Estimation for Medical Image Regis...

引用

Advancement in Renewable Energy and Intelligent Systems (AREIS), International conference on

作者： M. Priya S Perumal Sankar TocH Institute of Science and Technology Ernakulum Kerala India Department of ECE TocH Institute of Science and Technology Ernakulum Kerala India

ISBN: (数字)9798350387230

ISBN: (纸本)9798350387247

image registration has become a major medical image computing technology over the past ten years, with applications ranging from computer-assisted therapy and surgery to computer-assisted diagnosis. A medical image registration model based on a Cross-Entropy-based Deep neural Network (CEL-DNN) is presented in this paper. First, pre-processing is done on fixed and moving images, removing noise and enhancing contrast. Next, the features of both images are retrieved and then matched using the Mahalanobis Distance-based Brute-Force Matcher (MD-BFM) approach. FIS is used to estimate the transformation parameters based on the matched features. The final aligned image is obtained by applying the parameters using the CEL-DNN model over the moving image. To show the proposed model's superior performance, it is finally benchmarked against existing models.

关键词： image registration Renewable energy sources Sensitivity Deformation Noise Surgery artificial neural networks Feature extraction Robustness Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Staistical features extraction in wavelet domain for texture classification

Staistical features extraction in wavelet domain for texture...

引用

International conference on image and Signal processing and their applications (ISPA)

作者： Soraya ZEHANI Abdeldjalil OUAHABI Malika MIMI Abdelmalik TALEB-AHMED Electrical Engineering department Biskra University Biskra Algeria Polytech Tours Imaging and Brain University of Tours Tours France Electrical Engineering department Mostaganem University Mostaganem Algeria IEMN DOAE UMR CNRS 8520 UPHF Valenciennes France

ISBN: (纸本)9781728131573

This paper presents a new approach for texture classification generalizing a well-known statistical features combining the fractal analysis by means of fractal dimension (FD) with the selection first and second order statistics features in the spatial and wavelet domain. The objective of our paper is to propose the features extraction using statistical parameters in the spatial domain and in wavelet domain with different wavelets, with and without preprocessing stage for the texture classification using neural networks for pattern recognition and studying the effect of the preprocessing and wavelets in classification accuracy. The extracted features are used as the input of the ANN classifier. The performance of the proposed methods are evaluated by using two classes of Brodatz database textures. Finally, classification assessment measures such as the confusion matrix, ROC curves and accuracy are applied to the proposed methods.

关键词： artificial neurals network (ANN) Discrete wavelet transform (DWT) Fractal dimension (FD) Preprocessing Statistical features extraction Texture analysis Feature extraction Wavelet domain texture analysis Pretreatment Taxonomy wavelets texture textures fractal analysis spatial domain

来源：评论

学校读者我要写书评

暂无评论

Resource-Aware Heterogeneous Cluster Scheduling System for Deep neural Network Training Tasks

Resource-Aware Heterogeneous Cluster Scheduling System for D...

引用

International conference on Computer and Communications (ICCC)

作者： Xiaoqing Gao Chuxuan Zeng Dan Huang Liang Du Nong Xiao School of Computer Science and Engineering Sun Yat-sen University Guangzhou China China Unicom Guangdong Branch Guangzhou China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Deep neural networks (DNNs) have become integral to various modern artificial intelligence applications. As DNN models grow in complexity, diverse accelerators are increasingly utilized for training. Current heterogeneous cluster schedulers recognize performance disparities among models across different GPU types, managing costly GPU resources for users. However, these schedulers often neglect the significance of auxiliary resources in allocation decisions, relying on a GPU-based proportional distribution for CPU and memory resources. This study investigates the sensitivity of various DNN models to auxiliary resources through empirical experiments, revealing that training throughput for image and speech models is highly reliant on CPU allocation, while language models exhibit lower sensitivity. In response, we developed Nexus, a resource-aware scheduler designed to optimize resource utilization in heterogeneous GPU clusters. Experimental results demonstrate that Nexus can reduce average task completion time by up to 2.26x compared to traditional scheduling systems.

关键词： Training Sensitivity Computational modeling Graphics processing units artificial neural networks Throughput Complexity theory Resource management artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Japanese phonetic feature extraction for automatic speech recognition

Japanese phonetic feature extraction for automatic speech re...

引用

International conference on Signal and image processing (ICSIP)

作者： Manoj Banik Qamrun Nahar Eity Nusrat Jahan Lisa Foyzul Hassan Aloke Kumar Saha Mohammad Nurul Huda Department of CSE Ahsanullah University of Science and Technology Dhaka Bangladesh Enosis Solutions Dhaka Bangladesh Department of CSE University of Asia Pacific Dhaka Bangladesh Department of CSE United International University Dhaka Bangladesh

This paper presents a method for extracting distinctive phonetic features (DPFs) for automatic speech recognition (ASR). The method comprises three stages: i) a acoustic feature extractor, ii) a multilayer neural network (MLN) and iii) a hidden Markov model (HMM) based classifier. At first stage, acoustic features, local features (LFs), are extracted from input speech. On the other stage, MLN generates a 45-dimentional DPF vector from the LFs of 75- dimentions. Finally, these 45-dimentional DPF vector is inserted into an HMM-based classifier to obtain phoneme strings. From the experiments on Japanese Newspaper Article Sentences (JNAS), it is observed that the proposed DPF extractor provides a higher phoneme correct rate and accuracy with fewer mixture components in the HMMs compared to the method based on mel frequency cepstral coefficients (MFCCs). Moreover, a higher correct rate for each phonetic feature is obtained using the proposed method.

关键词： Feature extraction Speech Speech recognition Hidden Markov models artificial neural networks Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Co-parent selection for fast region merging in pyramidal image segmentation

Co-parent selection for fast region merging in pyramidal ima...

引用

Workshops on image processing Theory, Tools and applications, IPTA

作者： Milos Stojmenovic Andres Solis-Montero Amiya Nayak University of Ottawa Canada

The goal of image segmentation is to partition an image into regions that are internally homogeneous and heterogeneous with respect to other neighbouring regions. We build on the pyramid image segmentation work by making a more efficient method by which children chose parents within the pyramid structure. Instead of considering only four immediate parents each child node considers the neighbours of its candidate parent, and the candidate parents of its neighbouring nodes in the same level. In this paper, we also introduce the concept of a co-parent node for possible region merging at the end of each iteration. The new parents of the former children are co-parent candidates as if they are similar. The co-parent is chosen to be the one with the largest receptive field among candidate co-parents. Each child then additionally considers one more candidate, the co-parent of the previous parent. Other steps in the algorithm, and its overall layout, were also improved. The new algorithm is tested on a set of images. Our algorithm is fast (produces segmentations within seconds), results in the correct segmentation of elongated and large regions, very simple compared to plethora of existing algorithms, and appears competitive in segmentation quality with the best publicly available implementations. The major improvement over is that it produces visually appealing results at earlier levels of pyramid segmentation, and not only at the top one.

关键词： image segmentation artificial neural networks Pixel

来源：评论

学校读者我要写书评

暂无评论

Overview of the imageCLEF 2024: Multimedia Retrieval in Medical applications 15th

Overview of the ImageCLEF 2024: Multimedia Retrieval in Medi...

引用

15th International conference of the Cross-Language-Evaluation-Forum-Association (CLEF)

作者： Ionescu, Bogdan Muller, Henning Dragulinescu, Ana-Maria Ruckert, Johannes Ben Abacha, Asma de Herrera, Alba Garcia Seco Bloch, Louise Brunge, Raphael Idrissi-Yaghir, Ahmad Schafer, Henning Schmidt, Cynthia Sabrina Pakull, Tabea M. G. Damm, Hendrik Bracke, Benjamin Friedrich, Christoph M. Andrei, Alexandra-Georgiana Prokopchuk, Yuri Karpenka, Dzmitry Radzhabov, Ahmedkhan Kovalev, Vassili Macaire, Cecile Schwab, Didier Lecouteux, Benjamin Esperanca-Rodier, Emmanuelle Yim, Wen-Wai Fu, Yujuan Sun, Zhaoyi Yetisgen, Meliha Xia, Fei Hicks, Steven A. Riegler, Michael A. Thambawita, Vajira Storas, Andrea Halvorsen, Pal Heinrich, Maximilian Kiesel, Johannes Potthast, Martin Stein, Benno Natl Univ Sci & Technol Politehn Bucharest Bucharest Romania Univ Appl Sci Western Switzerland HES SO Delemont Switzerland Univ Appl Sci & Arts Dept Comp Sci Dortmund Germany Microsoft Redmond WA USA Univ Essex Colchester Essex England UNED Madrid Spain Univ Hosp Essen Inst Artificial Intelligence Med Essen Germany Univ Hosp Essen Inst Transfus Med Essen Germany Belarusian Natl Acad Sci Minsk BELARUS Belarusian State Univ Minsk BELARUS Univ Grenoble Alpes INRIA CNRS Grenoble INPLIG F-38000 Grenoble France Univ Washington Seattle WA 98195 USA SimulaMet Oslo Norway Bauhaus Univ Weimar Weimar Germany Univ Kassel Kassel Germany HessianAI Darmstadt Germany ScaDSAI Leipzig Germany

ISBN: (纸本)9783031719073;9783031719080

This paper presents an overview of the imageCLEF 2024 lab, organized as part of the conference and Labs of the Evaluation Forum CLEF Labs 2024. imageCLEF, an ongoing evaluation event since 2003, encourages the evaluation of technologies for annotation, indexing and retrieval of multimodal data. The goal is to provide information access to large collections of data across various usage scenarios and domains. In 2024, the 22st edition of imageCLEF runs three main tasks: (i) a medical task, continuing the caption analysis, Visual Question Answering for colonoscopy images alongside GANs for medical images, and medical dialogue summarization;(ii) a novel task related to image retrieval/generation for arguments for visual communication, aimed at augmenting the effectiveness of arguments;and (iii)ToPicto, a new task focused on translating natural language, whether spoken or textual, into a sequence of pictograms. The benchmarking capaign was a real success and received the participation of over 35 groups submitting more than 220 runs.

关键词： Medical text summarization medical image caption analysis visual question answering Generative Adversarial networks (GANs) image retrieval translation of neural language imageCLEF lab

来源：评论

学校读者我要写书评

暂无评论

An efficient abnormal beat detection scheme from ECG signals using neural network and ensemble classifiers

An efficient abnormal beat detection scheme from ECG signals...

引用

International conference on Software, Knowledge Information, Industrial Management and applications (SKIMA)

作者： Diptangshu Pandit Li Zhang Nauman Aslam Chengyu Liu Alamgir Hossain Samiran Chattopadhyay Computer Intelligence Group Northumbria University Newcastle United Kingdom Institute of Cellular Medicine Newcastle University Newcastle United Kingdom Computational Intelligence Anglia Ruskin University Cambridge United Kingdom Department of Information Technology Jadavpur University Kolkata India

This paper presents an investigation into the development of an efficient scheme to detect abnormal beat from lead ii Electro Cardio Gram (ECG) signals. Firstly, a fast ECG feature extraction algorithm was proposed which could extract the locations, amplitudes waves and interval from lead ii ECG signal. We then created 11 customized features based on the outputs of the feature extraction algorithm. Then, we used these 11 features to train an artificial neural network and an ensemble classifier respectively for detecting the abnormal ECG beats. Three manually annotated databases were used for training and testing our system: MIT-BIH Arrhythmia, QT and European ST-T database availed from Physionet databank. The results showed that for an abnormal beat detection, the neural network classifier had an overall accuracy of 98.73% and the ensemble classifier with AdaBoost had 99.40%. Using time domain processing approach, the proposed scheme reduced overall computational complexity as compared to the existing methods with an aim to deploy on the mobile devices in the future to promote early and instant abnormal ECG beat detection.

关键词： Electrocardiography Feature extraction Databases Classification algorithms Algorithm design and analysis artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

A Framework for neural Network Inference on FPGA-Centric SmartNICs

A Framework for Neural Network Inference on FPGA-Centric Sma...

引用

International conference on Field Programmable Logic and applications

作者： Anqi Guo Tong Geng Yongan Zhang Pouya Haghi Chunshu Wu Cheng Tan Yingyan Lin Ang Li Martin Herbordt ECE Department Boston University Boston MA ECE Department University of Rochester Rochester NY Pacific Northwest National Laboratory Richland WA Rice University Houston TX Microsoft Redmond WA

FPGA-based SmartNICs offer great potential to significantly improve the performance of high-performance computing and warehouse data processing by tightly coupling support for reconfigurable data-intensive computation with cross-node communication thereby mitigating the von Neumann bottleneck. Existing work however has generally been limited in that it assumes an accelerator model where kernels are offloaded to SmartNICs with most control tasks left to the CPUs. This leads to frequent waiting reduced performance and scaling challenges. In this work we propose a new distributive data-centric computing framework named FCsN for reconfigurable SmartNIC-based systems. Through a lightweight task circulation execution model and its implementation architecture FCsN allows the complete detaching of NN kernel execution control logic system scheduling and network communication to the SmartNICs. This boosts performance by (i) avoiding control dependency with CPUs and (ii) supporting streaming NN kernel execution and network communication at line rate and in a very fine-grained manner. We demonstrate the efficiency and flexibility of FCsN using various types of neural network kernels and applications including deep neural networks (DNN) and graph neural networks (GNN) as these last are both irregular and data intensive they offer an especially robust demonstration. Evaluations using commonly-used neural network models and graph datasets show that a system with FCsN can achieve 10 × speedups over the MPI-based standard CPU baselines

关键词： Runtime Processor scheduling Computational modeling High performance computing neural networks artificial neural networks Programming

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264页 << < 228 229 230 231 232 233 234 235 236 237 > >>

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：