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1391-1400 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：

Single shot 2D3D image regisraton 10

Single shot 2D3D image regisraton

引用

10th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2017

作者： Xie, Yi Meng, Cai Guan, Shaoya Wang, Qi Beihang University School of Astronautics Beijng China

ISBN: (纸本)9781538619377

In this paper, we present a very deep, 11 weights layers, Convolutional Neural Network (CNN) regression model for single shot and real-time 2D/3D registration. Different from optimization-based methods, which iteratively optimize the transformation parameters over a scalar-valued metric function representing the quality of the registration, the proposed method exploits the information embedded in the appearances of the Digitally Reconstructed Radiograph(DRR) and X-ray images and employs CNN regressors to directly estimate the transformation parameters. Unlike previous CNN approach which adopts an indirect way to cast the original complicated problem as several parts, we train a much deeper network to handle this registration problem by continuing to endeep the Convolutional Neural Network. To fit zooming in and out of DRRs more effectively we further more design a multi scale convolution kernel network. Our experiment results demonstrate the advantage of the proposed method in computational efficiency and accuray. The research may indicate that powerful Convolutional Neural Network can learn the highly complex regression function that mapping the raw image data to the registration parameters thus achieve high accuracy and real-time in 2D/3Dregistration in a direct way. © 2017 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Tongue image Segmentation via Thresholding and Clustering 10

Tongue Image Segmentation via Thresholding and Clustering

引用

10th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Li, Zuoyong Yu, Zhaochai Liu, Weixia Hu, Jinmei Lin, Yaming Zhang, Zuchang Minjiang Univ Fujian Prov Key Lab Informat Proc & Intelligent C Fuzhou Fujian Peoples R China Minjiang Univ Straits Inst Fuzhou Fujian Peoples R China Minjiang Univ Fujian Coll Res Base Humanities & Social Sci Internet Innovat Res Ctr Fuzhou Fujian Peoples R China Fuzhou Digital Hlth Ind Technol Innovat Ctr Fuzhou Fujian Peoples R China

ISBN: (纸本)9781538619377

Tongue diagnosis is widely used in Traditional Chinese Medicine (TCM). Tongue image segmentation plays a key role in developing an automatic tongue diagnosis system. To achieve tongue image segmentation (i. e., extraction of tongue body), we propose a method based on image thresholding and image clustering. The proposed method first finds an initial object region mainly containing the tongue body and the upper lip by transforming and thresholding on the hue component of an image in HSI color space, as well as subsequent morphological operations. Then, our method performs image clustering on the RGB components of the initial object region to seek the gap region between the tongue body root and the upper lip. Finally, the tongue body is extracted from the initial object region by removing fake tongue body regions such as the upper lip with the help of the gap region. Experiment results on a series of tongue images demonstrate the effectiveness of the proposed method.

关键词： image thresholding image clustering HSI RGB morphological operation tongue image segmentation

来源：评论

学校读者我要写书评

暂无评论

Combined local and global image enhancement algorithm 16

Combined local and global image enhancement algorithm

引用

16th image processing: Algorithms and Systems Symposium 2018

作者： Voronin, V. Semenishchev, E. Ponomarenko, M. Agaian, S. Don State Technical University Dept. of Radio-Electronics Systems Gagarina 1 Rostov on Don Russia Tampere University of Technology Tampere Finland CUNY College of Staten Island Dept. of Computer Science New YorkNY United States

We present a new image enhancement algorithm based on combined local and global image processing. The basic idea is to apply α-rooting image enhancement approach for different image blocks. For this purpose, we split image in moving windows on disjoint blocks with different size (8 by 8, 16 by 16, 32 by 32 and, i.e.). The parameter alfa for every block driven through optimization of measure of enhancement (EME). The resulting image is a weighted mean of all processing blocks. This strategy for image enhancement allows getting more contrast image with the following properties: irregular lighting and brightness gradient. Some experimental results are presented to illustrate the performance of the proposed algorithm. © 2018 Society for Imaging Science and Technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Music emotion understanding by computer based on BP neural network 10

Music emotion understanding by computer based on BP neural n...

引用

10th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2017

作者： Liu, Jun Huang, Min College of Music Nanchang Hangkong University Nanchang China College of Information Engineering Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781538619377

In order to enable the computer to recognize the emotion expressed in the music, a new method was developed in this paper. Firstly, we divided the emotion space into four parts according to Thayer model. Secondly, we extracted eight features from the music and finally a BP neural network was created to classify the music in the emotion space. The result shown the computer recognition is high coincident with the expert recognition and the reliability of the method was proved. © 2017 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Auto Coder-Decoder (CODEC) Model based Sparse Representation for image Super Resolution 10

Auto Coder-Decoder (CODEC) Model based Sparse Representation...

引用

10th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Zhang, Qieshi Gu, Liyan Cheng, Jun Wu, Xiaojun Kamata, Sei-ichiro Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab Virtual Real & Human Interact Te Beijing Peoples R China Shaanxi Normal Univ Key Lab Modern Teaching Technol Minist Educ Xian Shaanxi Peoples R China Shaanxi Normal Univ Sch Comp Sci Xian Shaanxi Peoples R China Huawei Technol Co Ltd Channel Algorithm Platform Dept Shenzhen Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Waseda Univ Grad Sch Informat Prod & Syst Tokyo Japan

ISBN: (纸本)9781538619377

In our daily life, the high quality image is widely used in varieties of fields, but sometimes we cannot capture the image with idea resolution due to some influences. For solving the resolution limitation of imaging sensors, the image super resolution (SR) representation technology is widely researched. Considering the advantage of sparse representation, the dictionary learning based methods is widely studied. However, landmark atoms cannot provide the representations of images, since the general feature extractors is universally applicable in feature extraction. To overcome the drawbacks, an auto coder-decoder (CODEC) model is proposed to extract representative features from low resolution (LR) images. The experimental results indicate the proposed method can obtain better effect than other methods.

关键词： Auto Cdoer-Decoder (CODEC) Model Data-Dependent Feature Extractor (DDFE) Sparse Representation Super Resolution (SR)

来源：评论

学校读者我要写书评

暂无评论

Comparison of non-negative matrix factorization and convolution kernel compensation in surface electromyograms of forearm muscles 10

Comparison of non-negative matrix factorization and convolut...

引用

10th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2017

作者： Šavc, M. Glaser, V. Holobar, A. Cikajlo, I. Matjačić, Z. Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia University Rehabilitation Institute Republic of Slovenia Ljubljana Slovenia

ISBN: (纸本)9781538619377

This contribution compares performances of nonnegative matrix factorization and high-density surface electromyogram (EMG) decomposition on EMG signals recoded from forearm muscles of young healthy subjects. During the EMG measurements, subjects performed dynamic wrist extensions and flexions and universal haptic device robot was used to oppose their movements and to measure wrist kinematics and excreted muscle forces. Recoded EMG signals were independently decomposed by Convolution Kernel Compensation technique and by alternating least squares non-negative matrix factorization. The identified motor unit discharge patterns were summed into cumulative spike trains and compared with non-negative components in each measurement. The results demonstrated good match (average correlation coefficient of 0.92 ± 0.06), but several discrepancies between the identified components have also been observed. In particular, when limiting the time support of identified components to active EMG signal portions only, the average correlation coefficient dropped to 0.72 ±0.20. © 2017 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks Based Transfer Learning for Diabetic Retinopathy Fundus image Classification 10

Convolutional Neural Networks Based Transfer Learning for Di...

引用

10th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Li, Xiaogang Pang, Tiantian Xiong, Biao Liu, Weixiang Liang, Ping Wang, Tianfu Shenzhen Univ Hlth Sci Ctr Shenzhen 518060 Peoples R China Shenzhen Univ Sch Biomed Engn Shenzhen 518060 Peoples R China Guangdong Key Lab Biomed Measurements & Ultrasoun Shenzhen 518060 Peoples R China Natl Reg Key Technol Engn Lab Med Ultrasound Shenzhen 518060 Peoples R China

ISBN: (纸本)9781538619377

Convolutional Neural Networks (CNNs) have gained remarkable success in computer vision, which is mostly owe to their ability that enables learning rich image representations from large-scale annotated data. In the field of medical image analysis, large amounts of annotated data may be not always available. The number of acquired ground-truth data is sometimes insufficient to train the CNNs without overfitting and convergence issues from scratch. Hence application of the deep CNNs is a challenge in medical imaging domain. However, transfer learning techniques are shown to provide solutions for this challenge. In this paper, our target task is to implement diabetic retinopathy fundus image classification using CNNs based transfer learning. Experiments are performed on 1014 and 1200 fundus images from two publicly available DR1 and MESSIDOR datasets. In order to complete the target task, we carry out experiments using three different methods: 1) fine-tuning all network layers of each of different pre-trained CNN models;2) fine-tuning a pre-trained CNN model in a layer-wise manner;3) using pre-trained CNN models to extract features from fundus images, and then training support vector machines using these features. Experimental results show that convolutional neural networks based transfer learning can achieve better classification results in our task with small datasets (target domain), by taking advantage of knowledge learned from other related tasks with larger datasets (source domain). Transfer learning is a promising technique that promotes the use of deep CNNs in medical field with limited amounts of data.

关键词： Convolutional neural networks transfer learning fine-tuning diabetic retinopathy fundus images classification

来源：评论

学校读者我要写书评

暂无评论

引用

10th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2017

作者： Li, Yi Liu, Xiaodong Research Center of Information and Control Dalian University of Technology Dalian China Technology of Computer and Information Engineering Heilongjiang University of Science Harbin China

ISBN: (纸本)9781538619377

In this paper, a maximum similarity criterion is proposed which is adapted to a new fuzzy face recognition method (namely, 2DFMS). The similarity degree between faces is defined by a nonlinear function. Based on this similarity, an improvement fuzzy membership function is obtained by applying k-nearest neighbor. Then, 2DFMS extracts the features from face images directly so that it will not suffer from the SSS problem. Finally, in the projected space, the test image is identified according to a specific classifier, which is based on a maximum similarity criterion. The whole algorithm is implemented on ORL and Yale face database to demonstrate the effectiveness and robustness. © 2017 IEEE.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Brain Emotional Oscillatory Activity during the Different Affective Picture and Sound Experience 10

Brain Emotional Oscillatory Activity during the Different Af...

引用

10th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Du, Ruoyu Lee, Hyo Jong Wei, Ran Nanjing Univ Posts & Telecommun Coll Geog & Biol Informat Nanjing Jiangsu Peoples R China Smart Hlth Big Data Anal & Locat Serv Engn Lab Ji Nanjing Jiangsu Peoples R China Chonbuk Natl Univ Div Comp Sci & Engn Jeonju South Korea Chonbuk Natl Univ Ctr Adv Image & Informat Technol Jeonju South Korea Tianjin Polytech Univ Sch Elect & Informat Engn Tianjin Peoples R China Tianjin Key Lab Optoelect Detect Technol & Syst Tianjin Peoples R China

ISBN: (纸本)9781538619377

Good mood state is an important indicator of good healthy life, while the bad emotional state could give rise to some social or mental state health issues. To properly manage the psychological and emotional health caused by negative emotions in our daily life, we need to recognize the various emotional states firstly. In order to find out the special cognitive emotional characteristics to reach high emotional identification accuracy, the aim of this paper is to explore the brain emotional oscillatory activity induced by visual and audio stimuli from IAPS and IADS databases in the amplitude measurement. Event related potential (ERP) analysis is used to find out the pronounced emotional characteristics in the emotion recognition. Thirty subjects are employed in the visual and audio experiments. A significance level of p < 0.01 is combined with ERP to analyze the brain signal data in order to discover significant effects. The results show that, two narrow time ranges (650-750ms and 800-900ms) in the late positive potential (LPP) are come up with five emotional states in the several brain regions for the visual induced emotion state changes. Six narrow time ranges from 0 to 1s of ERP are proposed to study potential various with three emotional states in the several brain regions for the audio induced emotion state changes. The results provide preliminary evidence for narrowing the time range of ERP in the emotion recognition research.

关键词： EEG Late positive potential (LPP) Human emotion Event related potential (ERP) IAPS IADS ANOVA

来源：评论

学校读者我要写书评

暂无评论

MM-PBSA: Challenges and opportunities 10

MM-PBSA: Challenges and opportunities

引用

10th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2017

作者： Do Vale Hipolito Cavalheiro, Joao Pedro Pires, Nuno Miguel Matos Dong, Tao Institute of Applied Micro-Nano Science and Technology-IAMNST Chongqing Key Laboratory of Colleges Universities On Micro-Nano Systems Technology and Smart Transducing Chongqing Engineering Laboratory for Detection Control and Integrated System National Research Base of Intelligent Manufacturing Service Chongqing Technology and Business University Chongqing China Department of Microsystems-IMS Faculty of Technology Natural Sciences and Maritime Sciences University College of Southeast Norway Kongsberg Norway P.O. Box 5003 ÅsN-1432 Norway

ISBN: (纸本)9781538619377

Molecular Mechanics Poisson-Boltzmann Surface Area (MM-PBSA) is arguably the most popular method for free binding energy prediction since it is considerably more accurate than docking or scoring methods, but considerably less demanding than Free Energy Perturbation (FEP). In this review, the most important challenges and opportunities associated to this method were addressed and evaluated. The following conclusions were obtained: Accuracy of MM-PBSA calculations still strongly depends on the settings used for the prediction, the conditions in which Molecular Dynamics simulations (MD) are made, the conditions from which the experimental data are obtained, it depends on the presence of the complex structure and this method has also shown to be unable to provide accurate results for charged molecules. On the other hand, it presents many opportunities since many improvements were based on MM-PBSA calculations such as Single Amino Acid Mutation based change in Binding free Energy (SAAMBE), bootstrap, dampened Molecular Mechanics Poisson-Boltzmann Surface Area (dMM-PBSA), a high throughput method called g-mmpbsa, a method based on both MM-PBSA calculations and a scoring function, force fields for inhomogeneous protein specific environments and many other new ways of improving the accuracy of this promising method. This study intends to clarify what are the major trends in this field and thus contribute to increase MM-PBSA's applicability and efficiency. © 2017 IEEE.

关键词： Molecular dynamics

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 << < 136 137 138 139 140 141 142 143 144 145 > >>

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：