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

2,004 篇 会议
27 册 图书
9 篇 期刊文献

馆藏范围

2,040 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,276 篇 工学
- 602 篇 生物医学工程（可授...
- 425 篇 计算机科学与技术...
- 388 篇 软件工程
- 377 篇 电气工程
- 349 篇 机械工程
- 251 篇 信息与通信工程
- 186 篇 生物工程
- 179 篇 光学工程
- 115 篇 电子科学与技术（可...
- 72 篇 控制科学与工程
- 69 篇 仪器科学与技术
- 55 篇 化学工程与技术
- 27 篇 安全科学与工程
- 23 篇 土木工程
- 22 篇 建筑学
- 16 篇 力学（可授工学、理...
- 16 篇 材料科学与工程（可...
461 篇 理学
- 196 篇 数学
- 186 篇 物理学
- 183 篇 生物学
- 66 篇 统计学（可授理学、...
- 62 篇 化学
- 24 篇 系统科学
407 篇 医学
- 403 篇 临床医学
- 197 篇 基础医学(可授医学...
- 113 篇 药学(可授医学、理...
- 35 篇 公共卫生与预防医...
113 篇 管理学
- 73 篇 图书情报与档案管...
- 47 篇 管理科学与工程(可...
- 19 篇 工商管理
16 篇 法学
10 篇 经济学
9 篇 农学
4 篇 艺术学
3 篇 教育学
3 篇 军事学
2 篇 文学

主题

179 篇 feature extracti...
130 篇 image segmentati...
124 篇 signal processin...
93 篇 training
89 篇 informatics
87 篇 signal processin...
70 篇 image reconstruc...
69 篇 biomedical imagi...
66 篇 accuracy
51 篇 biomedical engin...
49 篇 image color anal...
48 篇 deep learning
48 篇 image edge detec...
47 篇 visualization
46 篇 convolution
44 篇 electroencephalo...
43 篇 support vector m...
42 篇 mathematical mod...
39 篇 biological syste...
37 篇 three-dimensiona...

机构

22 篇 school of inform...
20 篇 beijing-dublin i...
19 篇 school of electr...
19 篇 school of biomed...
19 篇 the adapt sfi re...
18 篇 school of commun...
18 篇 school of electr...
14 篇 lepu medical ele...
14 篇 school of contro...
13 篇 school of comput...
13 篇 school of inform...
12 篇 shanghai key lab...
11 篇 suzhou institute...
11 篇 school of comput...
10 篇 school of comput...
9 篇 school of comput...
9 篇 school of commun...
9 篇 school of biomed...
9 篇 school of intern...
9 篇 school of inform...

作者

21 篇 li jin
19 篇 ke li
18 篇 wang jun
17 篇 chen xiang
16 篇 li qingli
16 篇 li ke
15 篇 jin li
14 篇 xiang chen
13 篇 sun jinping
13 篇 shan liu
12 篇 jun wang
12 篇 liu zhi
10 篇 zhou mei
10 篇 dev soumyabrata
10 篇 qingli li
9 篇 diao shengxi
9 篇 soumyabrata dev
8 篇 yen-wei chen
8 篇 zhenyu zhang
8 篇 jin hua

语言

1,799 篇 英文
237 篇 其他
8 篇 中文
1 篇 德文

检索条件"任意字段=International Congress on Image and Signal Processing, BioMedical Engineering and Informatics"

共 2040 条记录，以下是1191-1200 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：

Water Quality Monitoring of the Yangtze Estuary by Using GF-5 Hyperspectral image

Water Quality Monitoring of the Yangtze Estuary by Using GF-...

引用

international congress on image and signal processing, biomedical engineering and informatics

作者： Qinhua Gu Qingli Li Mei Zhou Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China

Ocean color remote sensing is one of the important means to monitor the spatial distribution of water quality parameters and to assess the estuarine environment. The successful launch of Gaofen-5 (GF-5) satellite provides researchers a high-resolution alternative for monitoring water quality. As the GF-5 satellite is put into use officially, to explore the practical capability of GF-5 satellite for water color remote sensing, this study takes the Yangtze river estuary as an example. Two GF-5 hyperspectral images acquired on March 27, 2019 are processed to estimate the chlorophyll-a concentration (C_(chla)) and suspended sediment concentration (SSC) in the Yangtze river estuary. Compared with water samples and other studies in Yangtze Estuary, the retrieved remote sensing reflectance (R_(rs)) is the same as the spectrum of high turbidity water body. Additionally, the obtained parameter value range and spatial distribution of Yangtze river estuary water quality parameters in dry season are consistent with previous studies and natural laws. The application effect of GF-5 hyperspectral image is ideal, and our future study will further exploit the potential of GF-5.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Denoising Auto-encoders for image Denoising 11

Improved Denoising Auto-encoders for Image Denoising

引用

11th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Xiang, Qian Pang, Xuliang Wuchang Inst Technol Coll Informat Engn Wuhan Hubei Peoples R China Wuhan Univ Engn Coll Elect & Informat Wuhan Hubei Peoples R China

ISBN: (纸本)9781538676042

image denoising is an important pre-processing step in image analysis. Various denoising algorithms, such as BM3D, PCD and K-SVD, obtain remarkable effects. Recently a deep denoising auto-encoder has been proposed and shown excellent performance compared to conventional image denoising algorithms. In this paper, we study the statistical features of restored image residuals produced by Denoising Auto-encoders and propose an improved training loss function for Denoising Auto-encoders based on Method noise and entropy maximization principle, with residual statistics as constraint conditions. We compare it with conventional denoising algorithms including original Denoising Auto-encoders, BM3D, total variation (TV) minimization, and non-local mean (NLM) algorithms. Experiments indicate that the Improved Denoising Autoencoders introduce less non-existent artifacts and are more robustness than other state-of-the-art denoising methods in both PSNR and SSIM indexes, especially under low SNR.

关键词： image Denoising Auto-encoders Method noise entropy maximization principle

来源：评论

学校读者我要写书评

暂无评论

Classification of Chromosome Karyotype Based on Faster-RCNN with the Segmatation and Enhancement Preprocessing Model

Classification of Chromosome Karyotype Based on Faster-RCNN ...

引用

international congress on image and signal processing, biomedical engineering and informatics

作者： Wei Ding Ling Chang Chaochen Gu Kaijie Wu Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China

Prenatal screening of chromosomal abnormalities is an important means of ensuring the healthy survival rate of newborns. The complex information and tedious workload of chromosome karyotype image analysis is a major difficulty in medical diagnosis. In this paper, a preprocessing model with object segmentation and feature enhancement is proposed. Combined with the framework of deep learning network, an automatic classification model for karyotype recognition of chromosomes is constructed. The preprocessing model studies the extraction of chromosome karyotype images at the pixel level and the feature enhancement of chromosome karyotype images. The model aims at providing more interpretable information for the deep learning network. In this paper, the algorithm analysis of chromosome karyotype preprocessing is carried out, the classification recognition network is built, and the detection results of the network verify the positive role of the preprocessing model. The model of chromosome karyotype automatic analysis based upon deep learning network may provide accurate reference information for doctors and reduce the workload of repeated diagnoses, which has very high application values.

关键词： Biological cells Deep learning image segmentation Feature extraction Proposals Task analysis Analytical models

来源：评论

学校读者我要写书评

暂无评论

Fast image Registration by LB Method 11

Fast Image Registration by LB Method

引用

11th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Chen, Yu Courbebaisse, Guy Lu, Dongxiang Yancheng Teachers Univ Sch Informat Engn 50 Kaifang Ave Yancheng 224002 Jiangsu Peoples R China Univ Claude Bernard Lyon 1 Univ Lyon UJM St Etienne U1206INSA LyonCNRSINSERMCREATISUMR 5220 F-69621 Lyon France

ISBN: (纸本)9781538676042

image registration is a key pre-procedure for high level image processing. However, for the complexity and accuracy of the algorithm, the image registration algorithm always has high time complexity. This means it is not suitable for realtime image processing, such as real-time target tracking. To speed up the registration algorithm, parallel computation is a good solution, for example, parallelizing the algorithm by LB method. In this paper, we proposed a LB based model for image registration. The main idea of our method consists in simulating the convection diffusion equation by establishing a LB model. Experiments shows our model is effective. Theoretically, our model can not get more accurate registration than the classical numerical method. But as a kind of numerical tool, our model is stable and faster, the most important is the potential for parallel image processing.

关键词： Lattice Boltzmann Model image Registration Partial Differential Equation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Position Error in Breast Cancer with Intensity Modulated Radiation Therapy

Analysis of Position Error in Breast Cancer with Intensity M...

引用

international congress on image and signal processing, biomedical engineering and informatics

作者： Wei Peng Haidong Liu Yuan Zhao School of Biomedical Engineering Hubei University of Science and Technology Xianning China

The the position error plays an important role in the therapy of breast cancer with intensity-modulated radiation therapy (IMRT) by image-guided technique. In order to explore the methods of reducing the position error, fifteen breast cancer patients with image-guided radiotherapy were selected in this study. The images of patients were scanned using the Versa HD imaging system. The position errors were obtained and analyzed by comparing the images between the simulating CT images and the Versa HD images in four directions, X (left and right), Y (head and foot), Z (belly back) and RTN (rotation angle). It is found that the frequencies of the absolute values of the X, Y, and Z direction position errors exceed 1mm are 40%, 66.6%, and 60% respectively, and the frequencies of which exceed 2mm are 26.6% 26.6% and 60%. The average values of the errors of X, Y, Z, and RTN are 0.91mm, 1.45mm, 2.57mm, and 0.39deg, respectively. The position error takes place most in the Y direction, and least in the X direction. According to the differences between the simulating CT images and the Versa HD images, the position errors were obtained and analyzed. The relations between the errors and the directions can by applied in the real-time correction of the treatment of breast cancer patients with image guidance technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Automatic Detection of Workplace Behavior Using Ballistocardiographic signals

Towards Automatic Detection of Workplace Behavior Using Ball...

引用

international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Ruidong Ding Chuanmin Wu Gang Shen School of Software Engineering Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Workplace stress may cause severe damage to employees' physical and mental health. Successful stress management closely depends on the effective monitoring of peoples everyday behaviors. In this paper, we design a workplace behavior monitoring system that collects the ballistocardiographic (BCG) signals using piezoelectric sensors mounted inside the cushions of office chairs. In addition to being able to reflect the body displacement along with the ventricle contraction, the BCG signals also contain multiple sources of interferences, and thus can be used to detect the modes of the body motions. An ensemble machine learning scheme is developed to classify the BCG waveform into several categories, including off-seat, sedate, working and in motion. When an employee is in a sedate position, the BCG samples can be further processed to observe the cardiovascular activities. These temporal classified results can be analyzed to establish the individual employee's office profile. Compared with the recorded baseline, early intervention is made possible when needed. The proposed system has been tested with 12 subjects, and the preliminary results demonstrate its potential application in the real world workplace environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Security Anlysis of Certificateless Aggregate Signature Scheme in VANETs

Security Anlysis of Certificateless Aggregate Signature Sche...

引用

international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Xiaoming Hu Wenan Tan Chengcheng Yu Chuang Ma Huajie Xu College of Computer and Information Engineering Shanghai Polytechnic University Shanghai China Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China

Certificateless aggregate signature (CLASS) scheme which combines on certificateless signature and aggregation signature solves the identity-based (ID) public key infrastructure (PKI)'s key escrow problem, the PK problem of traditional PKI. So, CLASS schemes can be applied in many fields to solve the privacy problem and security problem, for example in the information network and system of medicine and biology. Also there are many CLASS schemes to be proposed for these fields. In this manuscript, we analyze the CLASS scheme for VANETs proposed in 2018 which is more efficient than other similar schemes. We find which the CLASS scheme cannot satisfy the security the following two properties, namely unforgeability and traceability as they claimed. That is to say that the attacker may forge a correct signature and it may pass the signature verification but the attacker unknows the secret key. So, the CLASS scheme is not suitable for applying in any system. As an improving, after analyzing original scheme, it is found that the key problems for being insecure and give one simple method to solve the existed drawbacks.

关键词： Aggregates Public key Handwriting recognition Biology Computer security Registers

来源：评论

学校读者我要写书评

暂无评论

Steganalysis Using Unsupervised End-to-end CNN Fused with Residual image 11

Steganalysis Using Unsupervised End-to-end CNN Fused with Re...

引用

11th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Wu, Yao Yi, Junkai Li, Hui Beijing Univ Chem Technol Coll Informat Sci & Technol Being Peoples R China Beijing Informat Sci & Technol Univ Cyberspace Secur Res Inst Being Peoples R China

ISBN: (纸本)9781538676042

Recently, convolutional neural networks (CNNs) has been used in the field of image steganalysis. However, there are still many deficiencies. In order to improve the detection accuracy, we propose an unsupervised end-to-end CNN to extract image features of the stego images. The end-to-end mapping can be trained to learn the most effective characteristic expression from input images to output images. By integrating hidden layers of the deep CNN, the extracted features can be considered as having characteristics of both input images and its residual images. In this way, we try to minimize the negative effect of the high-pass filtering under the condition of guaranteeing the convergence of the network. The experimental results show that the end-to-end CNN maintains good performance on BOSSBase even when the embedding rate is 0.1 bpp.

关键词： component Convolutional neural networks (CNNs) end-to-end deep learning steganalysis

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Deep Hybrid Long Short-Term Memory and Restricted Boltzmann Machine Network for Urban Traffic Speed Prediction

Fine-Tuning Deep Hybrid Long Short-Term Memory and Restricte...

引用

international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Yuanyuan Ni Zongtao Duan Kai Zhang Jihai Yang Yun Yang School of Information and Engineering Chang'an University Xi'an China

Accurate urban traffic speed prediction plays a crucial role in intelligent transportation systems (ITSs). However, the potential spatial-temporal information of big urban traffic data captured from the complex behaviors of urban systems cannot be efficiently mined based on the state-of-art intelligent models. Therefore, we propose a hybrid Long Short-Term Memory (LSTM) and Restricted Boltzmann Machine (RBM) neural network with a fine-tuning strategy for urban traffic speed prediction. Firstly, the LSTM-RBM model dynamically combines the LSTM and RBM, such that the LSTM extracts the time-varying characteristics of the speed sequences to dynamically adjust the RBM, and then the RBM can capture the deep and detailed features of the speed sequences in the optimal way. Secondly, a transfer learning fine-tuning strategy is proposed to effectively pre-train the LSTM-RBM to achieve higher accuracy. Experimental results based on traffic speed data of the second ring road in Xi'an indicate that the proposed hybrid LSTM-RBM model with fine-tuning can outperform the existing deep models.

关键词： Feature extraction Roads Data models Predictive models Public transportation Logic gates Neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Fabric patterns image Based on Improved Log-AlexNet 11

Classification of Fabric patterns Image Based on Improved Lo...

引用

11th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Feng, Maoshuang Chen, Dongfang Wang, Xiaofeng Wuhan Univ Sci & Technol Coll Comp Sci & Technol Hubei Prov Key Lab Intelligent Informat Proc & Re Wuhan 430065 Hubei Peoples R China

ISBN: (纸本)9781538676042

Fabrics are filled with aspects of our lives. Facing the massive fabric image data, how to help people quickly and efficiently classify these images becomes urgent. Aiming at the problem of low classification efficiency and accuracy, this paper proposes a binary hash classification framework based on AlexNet. By improving the activation function Log-ReLU and adding hidden layer to learn binary hash coding and other optimized network parameters, the proposed framework (Log-AlexNet) extracts rich abstract features and improves the classification efficiency and precision of fabric patterns. Compared with the traditional image feature extraction and classification methods, the experimental results show that the improved Log-AlexNet for classification of cloth fabric patterns is feasible and much better than the traditional state-of-the-art methods.

关键词： component Convolutional Neural Network Fabric patterns Classification Binary hash encoding activation function

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204页 << < 116 117 118 119 120 121 122 123 124 125 > >>

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：