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

3,924 篇 会议
158 篇 期刊文献
36 册 图书
1 篇 学位论文

馆藏范围

4,119 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,944 篇 工学
- 1,879 篇 计算机科学与技术...
- 1,269 篇 电气工程
- 1,087 篇 信息与通信工程
- 1,079 篇 软件工程
- 302 篇 光学工程
- 293 篇 电子科学与技术（可...
- 286 篇 仪器科学与技术
- 264 篇 生物医学工程（可授...
- 207 篇 控制科学与工程
- 153 篇 机械工程
- 144 篇 生物工程
- 81 篇 化学工程与技术
- 63 篇 材料科学与工程（可...
- 46 篇 动力工程及工程热...
- 35 篇 土木工程
- 35 篇 航空宇航科学与技...
- 33 篇 建筑学
- 33 篇 轻工技术与工程
- 32 篇 测绘科学与技术
1,432 篇 理学
- 794 篇 数学
- 620 篇 物理学
- 218 篇 系统科学
- 170 篇 生物学
- 158 篇 统计学（可授理学、...
- 85 篇 化学
739 篇 医学
- 717 篇 临床医学
- 112 篇 基础医学(可授医学...
- 83 篇 药学(可授医学、理...
236 篇 管理学
- 136 篇 管理科学与工程(可...
- 103 篇 图书情报与档案管...
30 篇 法学
22 篇 农学
18 篇 教育学
14 篇 军事学
11 篇 文学
8 篇 经济学
6 篇 艺术学

主题

317 篇 wavelet transfor...
243 篇 image processing
237 篇 discrete wavelet...
222 篇 image coding
214 篇 signal processin...
193 篇 feature extracti...
173 篇 image segmentati...
143 篇 signal processin...
131 篇 image enhancemen...
126 篇 wavelet transfor...
119 篇 image reconstruc...
117 篇 image compressio...
91 篇 wavelet analysis
78 篇 deep learning
72 篇 psnr
72 篇 accuracy
71 篇 image denoising
69 篇 robustness
67 篇 noise reduction
66 篇 digital signal p...

机构

7 篇 tianjin normal u...
7 篇 tsinghua univ
6 篇 university of sc...
6 篇 beijing inst tec...
6 篇 chinese acad of ...
6 篇 beijing jiaotong...
5 篇 northwest inst n...
5 篇 carleton univ de...
4 篇 natl univ def te...
4 篇 college of infor...
4 篇 univ elect sci &...
4 篇 university of pi...
4 篇 zhengzhou inform...
4 篇 school of electr...
4 篇 galgotias univer...
4 篇 nanyang technol ...
4 篇 hokkaido univ sa...
4 篇 school of electr...
4 篇 institute of met...
4 篇 xidian univ sch ...

作者

7 篇 hasan demirel
6 篇 gao w
6 篇 gholamreza anbar...
6 篇 xiong gang
6 篇 liu ying
5 篇 murat ceylan
5 篇 ceylan murat
5 篇 demirel hasan
5 篇 anbarjafari ghol...
5 篇 rao g. sasibhush...
5 篇 yan zhang
5 篇 zhang yue
5 篇 zhao yao
5 篇 unser m
4 篇 bouridane ahmed
4 篇 li li
4 篇 dutta malay kish...
4 篇 zhu weile
4 篇 buggy t.
4 篇 shi fei

语言

3,983 篇 英文
68 篇 土耳其文
46 篇 其他
21 篇 中文
2 篇 俄文

检索条件"任意字段=4th Conference on Wavelet Applications in Signal and Image Processing"

共 4119 条记录，以下是4061-4070 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 Feature Weighting Method for Mangrove Pests image Classification with Heavy-tailed Distributions 2020

A Dynamic Feature Weighting Method for Mangrove Pests Image ...

引用

Proceedings of the 2020 4th International conference on Vision, image and signal processing

作者： Zixu Wang Weiguo Gong Weihong Li Key Lab of Optoelectronic Technology & Systems of Education Ministry Chongqing University Chongqing China

ISBN: (纸本)9781450389532

Most of the data in agriculture and forest obey heavy-tailed distribution, in which the data distribution is extremely imbalanced and the amount of most classes is poor. In this paper, we propose a feature centroid based dynamic feature weighting method between head and tail classes for mangrove pest images classification. In the proposed method, firstly, we design a convolutional neural network to extract the clustering centroid as a representation of the subclass. Secondly, we use the centroid feature memory to achieve the dynamic feature weighting through extraction, injection and fusion, which enrich the feature space of the tail classes while retaining identity. thirdly, to localize the pests in natural background, we optimize the weakly-supervised localization algorithm with a multiscale local maximum index strategy to extract saliency maps. Furthermore, to carry out our research we establish a heavy-tailed distributed image dataset named MIPDGC based on mangrove forest pest. the experimental results prove that the dynamic feature weighting method can obtain higher classification accuracy and better performance than other general methods on the classification accuracy of the MIPDGC.

关键词： Feature Weighting Classification Pests Mangrove Localization Heavy-tailed

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based implementation of IncCond algorithm for photovoltaic applications

FPGA-Based implementation of IncCond algorithm for photovolt...

引用

International conference on Microelectronics, ICM

作者： N. Chettibi A. Mellit M. Drif Faculty of Science and Technology Renewable Energy Laboratory Jijel University Jijel Algeria Electronics Department Msila University Msila Algeria

Recent advances in control algorithms embedded into a Field Programmable Gate Array (FPGA) allowed the application of such algorithms in real engineering problems (robotic, image and signal processing, control, power electronics, etc.), however, the application of such technologies in the solar energy field is very limited. the embedded advanced algorithm into FPGA can play a very important role in renewable energy systems for control, monitoring, supervision, etc. FPGA technology was employed due to its development, flexibility and low cost. In this paper, the incremental conductance (IncCond) algorithm is implemented on FPGA for tracking the Maximum Power Point (MPP) of a photovoltaic (PV) array. the IncCond algorithm has been designed using a description language (VHSIC standing for very-high-speed integrated circuits) then implemented on Xilinx Virtex-II-Pro(xc2v1000-4fg456. Modelsim-based simulation results confirm the good tracking efficiency (96%) and rapid response time (2ms). It has been confirmed that the implemented algorithm performs better than the well known Perturb and Observe (P&O) algorithm.

关键词： Field programmable gate arrays Algorithm design and analysis Photovoltaic systems signal processing algorithms Arrays Renewable energy sources

来源：评论

学校读者我要写书评

暂无评论

image Classification Based on IndCRNN Module 2020

Image Classification Based on IndCRNN Module

引用

Proceedings of the 2020 4th International conference on Vision, image and signal processing

作者： Huaqing Liao Zhejiang University Ningbo Institute of Technology zhejiang China

ISBN: (纸本)9781450389532

As a core of computer vision, image classification has become a hot topic in recent years. RNN framework can not only model sequence data, predict the trend of sequence data, but also show good results in image classification. In this paper, an improved model IndCRNN is proposed for the over-fitting phenomenon of Independent Recurrent Neural Network (IndRNN) in the training process. IndCRNN is the Independent Convolutional Recurrent Neural Network, which applies the convolutional idea of Convolutional Neural Network (CNN) to IndRNN. On the one hand, the dimension reduction can be realized. In the process of training iteration, the training time will be reduced due to the reduction of dimension. On the other hand, if the high-dimensional feature is taken as the input of IndRNN, the basis of the final output classification becomes the feature of two dimensions of space-time. Another advantage of IndCRNN is that it selects Leaky ReLU as the activation function, replaces the traditional ReLU activation function, maximizes the historical information of the training data, and reduces the vulnerability in the process of updating iterative training. Finally, we did an experiment with TensorFlow environment, experiment selects the MNIST dataset and permuted MNIST dataset. the IndCRNN model is compared with IRNN, LSTM, RNN and IndRNN on two datasets respectively. the experimental results show the feasibility and superiority of the proposed model.

关键词： Convolution Cyclic Neural Network Activation Function image Classification Gradient Disappearance

来源：评论

学校读者我要写书评

暂无评论

Decoding of Auditory Imagination Activity Based on Machine Learning Methods

Decoding of Auditory Imagination Activity Based on Machine L...

引用

Frontiers Technology of Information and Computer (ICFTIC), IEEE International conference on

作者： Wanly Ma Xuegang Tang Qiuqin Xia Yiwei Xu Weitong Gao Jin Gu Southwest Jiaotong University Chengdu China

the decoding of brain signals has important research value and is also full of challenges. In recent years, the fMRI technology is more and more widely used in the brain signals decoding because of its high spatial resolution and non-invasive characteristic. the existing brain region template provides a powerful tool for brain region decoding research, and the obtained functional connectivity matrix quantifies the correlation between brain regions. the development of pattern recognition technology has created a favorable technical foundation for the study of fMRI data, including a variety of mature machine learning methods such as support vector machine. In this paper, the fMRI data of 24 healthy subjects was measured when they performed the auditory imagination under different sound and scene conditions, then the functional connectivity matrices of brain regions were obtained and to be classified by several pattern recognition methods, such as optimized support vector machine, naive Bayes, and logistic regression. At last, the classification methods were compared according to the classification accuracy. Compared with related works, Methods of data acquisition and the accuracy of the results are better than previous job. the method can help psychologists and neuroscientists perform the brain signal decoding with high efficiency and quality. At the same time, the research is helpful to reveal the neural mechanism of auditory imagination and auditory perception, deepen our understanding of human brain auditory information processing, help the computer to simulate human hearing, and use the correlation of brain signals to help the deaf and mute people to carry out related activities, which has good social benefits.

关键词： Support vector machines Analytical models image recognition Correlation Computational modeling Machine learning Functional magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Improved Super-resolution Network based on SRCNN 21

Improved Super-resolution Network based on SRCNN

引用

Proceedings of the 2021 4th International conference on Algorithms, Computing and Artificial Intelligence

作者： Bin Yang Kai Xie Hongbo Pan Yuyan Chen Beijing Key Laboratory of Signal and Information Processing for High-end Printing Equipment Beijing Institute of Graphic Communication China School of Information Engineering Beijing Institute of Graphic Communication China

ISBN: (纸本)9781450385053

the process of recovering high-resolution images from one or more degraded low-resolution images is known as super-resolution reconstruction. the present super-resolution (SR) deep learning technique has certain limitations, because the deeper the network layer, the higher the training cost and time consumption. this paper, based on SRCNN, revamped the three-step reconstructed process of SRCNN by including VGG and residual ideas. Enhancing its network structure by utilizing subpixel convolution approach which can replace the step of image preprocessing and upscale in SRCNN algorithm. When comparing the reconstructed pictures of Set5, Set14, BSDS100, Urban100, and Manga109 data sets, the revised SRCNN structure outperforms the original SRCNN by 1.1dB in Peak signal to Noise Ratio (PSNR) and 0.026 in structural similarity (SSIM). When compared to other popular SR network except for SRCNN, the improved reconstructed network has fewer network layers, is easier to train, and produces higher reconstructed image quality than the original SRCNN.

关键词： Subpixel convolution VGG Residual Structure Super-resolution

来源：评论

学校读者我要写书评

暂无评论

Detection of Islanding Using Intelligent Classifiers for Integrated Solar Wind Power System

Detection of Islanding Using Intelligent Classifiers for Int...

引用

Sustainable Energy and Future Electric Transportation (SEFET), International conference on

作者： Bindu Vadlamudi Indira Damarla MLN Vital Subhojit Dawn Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada India

ISBN: (数字)9798350383997

ISBN: (纸本)9798350384000

Integration of distributed energy resources (DER), such as wind and solar power systems is increasing day-by-day to meet growth of power demand. Distributed generation (DG) integration has numerous technological advantages such as enhanced performance, security of system and quality of power. In addition to the benefits of integration of DG to grid we need to face some challenges that are caused due to the isolation nature of DGs. One of the major issues identified in the integration of DGs is islanding, which leads to power quality issues, damage of equipment and keeps the lives of utility works at risk. “To overcome this speed and accurate detection of islanding become necessary for the smooth operation of Micro Grid (MG) which can be achieved by implementing suitable Islanding detection technique”. In this paper a novel intelligent islanding detection method (IIDM) is implemented by integrating convolution neural network (CNN) with long short-term memory (LSTM) by using Empirical wavelet transform (EWT) technique for feature extraction of uncertainty signals at point of coupling of DGs to grid. To improve the accuracy and performance of the classifier CNN-LSTM (CL) network optimal weight selection is done by using Particle swarm Optimization algorithm (PSOA). the objective of the proposed classifier is to classify non-islanding and islanding events under various fault scenarios. the proposed classifier illustrated better performance in view of signal Noise Ratio (SNR) when tested with various noise levels. the results of MATLAB/Simulink clearly showed that implemented method categorized the state of islanding and non-islanding state more accurately when compared with existing islanding detection techniques.

关键词： Islanding Accuracy signal processing algorithms Wind power generation Feature extraction Distributed power generation Classification algorithms Power systems signal to noise ratio Noise level

来源：评论

学校读者我要写书评

暂无评论

Controlling the Position and Velocity in Space of the Quad-Rotor UAV *** Using Predictive Functional Control and image processing in Open CV

Controlling the Position and Velocity in Space of the Quad-R...

引用

2012 4th International conference on signal processing Systems(ICSPS 2012)

作者： Anusha Gururaj Jamkhandi Saee Tulpule Ashvini Chaturvedi Jean-Noel Charvet National Institute of Technology Ecole Catholique d'Arts et Metiers

the aim of this work is to use Predictive Functional Control (PFC) to make the Parrot Drone follow a red ball. the Drone has an in-built proportional-integral-derivative (PID) controller in its software development kit to control its motion. However, large time delays and high-order dynamics are the common dynamic characteristics that are difficult to control using PID technique. this work aims to use PFC instead of PID control due to its shortcomings. We begin with developing an equivalent first order process model for Drone motors and its PID controllers by analyzing the Euler angles (pitch, roll and yaw) and the velocities in the X and Y directions. the Drone is then made to follow a red ball for which the coordinates of its centre are determined through image processing using Hough circles in Open CV and subsequently these coordinates are passed to the PF controller. the X and Y positions are controlled by the PFC by manipulating pitch and roll angles respectively. the results obtained are quite promising and thereby an attempt is made to overcome the limitations of PID controllers to a significant degree by using PF controllers.

关键词： proportional-integral-derivative control, predictive functional control, euler angles, hough circles, set point, manipulated variable, controlled variable

来源：评论

学校读者我要写书评

暂无评论

CroP: Color Constancy Benchmark Dataset Generator 2020

CroP: Color Constancy Benchmark Dataset Generator

引用

Proceedings of the 2020 4th International conference on Vision, image and signal processing

作者： Nikola Banić Karlo Koščević Marko Subašić Sven Lončarić Gideon Brothers Radnička Zagreb Croatia University of Zagreb Unska Zagreb Croatia

ISBN: (纸本)9781450389532

Implementing color constancy as a pre-processing step in contemporary digital cameras is of significant importance as it removes the influence of scene illumination on object colors. Several benchmark color constancy datasets have been created for the purpose of developing and testing new color constancy methods. However, they all have numerous drawbacks including a small number of images, erroneously extracted ground-truth illuminations, long histories of misuses, violations of their stated assumptions, etc. To overcome such and similar problems, in this paper a color constancy benchmark dataset generator is proposed. For a given camera sensor it enables generation of any number of realistic raw images taken in a subset of the real world, namely images of printed photographs. Datasets with such images share many positive features with other existing real-world datasets, while some of the negative features are completely eliminated. the generated images can be successfully used to train methods that afterward achieve high accuracy on real-world datasets. this opens the way for creating large enough datasets for advanced deep learning techniques. Experimental results are presented and discussed. the source code is available at http://***/ipg/resources/colorconstancy/.

关键词： image Dataset Illumination Estimation Data Augmentation Color Constancy White Balancing

来源：评论

学校读者我要写书评

暂无评论

Freshness Recognition of Fruit and Vegetable images using GANs Series Data Augmentation 22

Freshness Recognition of Fruit and Vegetable Images using GA...

引用

Proceedings of the 2022 4th International conference on Video, signal and image processing

作者： Zhihong Zhao Jieshun You Yunong Cui School of Applied Science and Civil Engineering Beijing Institute of Technology Zhuhai China

ISBN: (纸本)9781450397810

the use of computer vision techniques to distinguish fresh from stale fruit has gained widespread acceptance in recent years. However, the scarcity of datasets in this field has made it more difficult for many of the research results to be accessible in real-life situations. the core idea of this paper is to improve the generalization of the training set and the performance of the classifier by augmenting the fruit and vegetable image dataset with neural networks. this paper will investigate the applicability of the established Conditional Generative Adversarial Nets (CGAN) in this domain and discover problems such as mode collapse. the contribution of this paper is to combine existing structures and propose novel adversarial generative networks for the fruit and vegetable image, including Conditional Wasserstein GAN with Gradient Penalty (CWGAN-GP) and Auxiliary Classifier Wasserstein GAN with Gradient Penalty (ACWGAN-GP). In addition, a pre-trained models with Spinal fully-connected layer and ProgressiveSpinal fully-connected layer was used to freshness classify. It was found that ACWGAN-GP, which combines multiple network structures, not only produced more realistic and diverse images in the fruit and vegetable domain, but also maintained the learning speed of a single model during the training. In addition, by adding synthetic images to the training, the fruit and vegetable freshness classifier achieves 100% accuracy on a specified validation set.

关键词： image generation Freshness recognition Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of CNN Models' Accuracy Using Synthetic and Original Datasets for Cotton Leaf Classification

Comparative Analysis of CNN Models' Accuracy Using Synthetic...

引用

Artificial Intelligence and signal processing (AISP), INDIA, International conference on

作者： Pujiita Srieya Bolisetty Lakkshmi Yogesh N A Siva Dhanush Kosuri Puppala Sravan Sivaraju Venkata Sai Karthik Rajesh C.B Department of Electronics and Communication Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350350654

ISBN: (纸本)9798350350661

In agriculture, finding diseases in plants as soon as possible is very important for getting the most crops and making sure there is enough food for everyone. A potential way to quickly and accurately diagnose diseases is to use Artificial Intelligence (AI) tools, especially image classification models. But the quality and variety of the training sample have a big impact on how well these models work. In many cases, it's hard to get a fair collection with enough samples. In order to solve this problem, we suggest a new way to classify cotton leaf diseases that uses both fake and real datasets. First, we use the Deep Convolutional Generative Adversarial Network (DCGAN) method to make a fake dataset. this makes fake pictures that look like the ones in the real dataset. After that, we use both the real and mixed datasets to train different Convolutional Neural Network (CNN) models, such as DenseNet121, InceptionV3, MobileNetV2, ResNet50, VGG16, and VGG19. To see how well each model does on both sets of data, evaluation measures like accuracy, Fl score, and classification results are used. Our results show that the accuracy rates of the combined dataset with simulated pictures are higher than those of the original dataset alone.

关键词： Training Analytical models Accuracy Crops signal processing Data augmentation Data models Convolutional neural networks Cotton Synthetic data

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412页 << < 403 404 405 406 407 408 409 410 411 412 > >>

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：