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

1,327 篇 会议
11 篇 期刊文献
9 册 图书

馆藏范围

1,347 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

915 篇 工学
- 757 篇 计算机科学与技术...
- 497 篇 软件工程
- 304 篇 信息与通信工程
- 205 篇 电气工程
- 175 篇 生物工程
- 127 篇 生物医学工程（可授...
- 107 篇 光学工程
- 90 篇 控制科学与工程
- 80 篇 电子科学与技术（可...
- 58 篇 仪器科学与技术
- 48 篇 机械工程
- 35 篇 化学工程与技术
- 28 篇 安全科学与工程
- 26 篇 交通运输工程
425 篇 理学
- 189 篇 生物学
- 187 篇 数学
- 151 篇 物理学
- 76 篇 统计学（可授理学、...
- 54 篇 系统科学
- 40 篇 化学
170 篇 管理学
- 106 篇 图书情报与档案管...
- 73 篇 管理科学与工程(可...
- 40 篇 工商管理
146 篇 医学
- 130 篇 临床医学
- 88 篇 基础医学(可授医学...
- 65 篇 药学(可授医学、理...
- 24 篇 公共卫生与预防医...
28 篇 教育学
- 28 篇 教育学
27 篇 法学
- 21 篇 社会学
18 篇 经济学
- 17 篇 应用经济学
16 篇 农学
5 篇 军事学
1 篇 文学
1 篇 历史学

主题

211 篇 machine learning
134 篇 deep learning
78 篇 signal processin...
72 篇 accuracy
71 篇 feature extracti...
68 篇 signal processin...
61 篇 support vector m...
57 篇 machine learning...
46 篇 predictive model...
33 篇 neural networks
32 篇 convolutional ne...
31 篇 random forests
29 篇 computational mo...
29 篇 training
26 篇 natural language...
26 篇 prediction algor...
21 篇 technological in...
20 篇 real-time system...
19 篇 adversarial mach...
18 篇 image processing

机构

16 篇 chitkara centre ...
14 篇 centre of resear...
12 篇 shenyang ligong ...
6 篇 chitkara univers...
6 篇 ai & ds vishwaka...
6 篇 school of inform...
5 篇 department of me...
5 篇 khulna universit...
5 篇 department of co...
4 篇 delhi technologi...
4 篇 heilongjiang uni...
4 篇 department of s&...
4 篇 beijing univ pos...
4 篇 it vishwakarma i...
4 篇 chitkara univers...
4 篇 department of co...
4 篇 sri lanka instit...
4 篇 advanced telecom...
4 篇 shenyang ligong ...
4 篇 graduate school ...

作者

6 篇 mehta shiva
5 篇 rasmita panigrah...
4 篇 neelamadhab padh...
4 篇 wang xin
3 篇 m. vigenesh
3 篇 baydeti nagaraju
3 篇 sinambela marzuk...
3 篇 santosh kumar sh...
3 篇 ganapati panda
3 篇 debendra muduli
3 篇 abujar sheikh
3 篇 a. sivanantham
3 篇 li yajie
3 篇 li aihua
3 篇 zhou feng
3 篇 islam md. sanzid...
2 篇 aira kharvel par...
2 篇 nokshangthemba
2 篇 maheswara rao v ...
2 篇 lee tzong-ru

语言

1,273 篇 英文
65 篇 其他
11 篇 中文

检索条件"任意字段=Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning"

共 1347 条记录，以下是1091-1100 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：

Deep Active learning for Text Classification 2018

Deep Active Learning for Text Classification

引用

2nd international conference on Vision, Image and signal processing (ICVISP)

作者： An, Bang Wu, Wenjun Han, Huimin Beihang Univ 37 XueYuan Rd Beijing Peoples R China

ISBN: (纸本)9781450365291

In recent years, Active learning (AL) has been applied in the domain of text classification successfully. However, traditional methods need researchers to pay attention to feature extraction of datasets and different features will influence the final accuracy seriously. In this paper, we propose a new method that uses Recurrent Neutral Network (RNN) as the acquisition function in Active learning called Deep Active learning (DAL). For DAL, there is no need to consider how to extract features because RNN can use its internal state to process sequences of inputs. We have proved that DAL can achieve the accuracy that cannot be reached by traditional Active learning methods when dealing with text classification. What's more, DAL can decrease the need of the great number of labeled instances for Deep learning (DL). At the same time, we design a strategy to distribute label work to different workers. We have proved by using a proper batch size of instance, we can save much time but not decrease the model's accuracy. Based on this, we provide batch of instances for different workers and the size of batch is determined by worker's ability and scale of dataset, meanwhile, it can be updated with the performance of the workers.

关键词： Active learning Deep learning machine learning Artificial Intelligence Text Classification

来源：评论

学校读者我要写书评

暂无评论

An Improved Visual Robot Moving Target Tracking Method

An Improved Visual Robot Moving Target Tracking Method

引用

IEEE international conference on Information Communication and signal processing (ICICSP)

作者： Hao Liu Hong Zhou Jincheng College of Sichuan University Chengdu China

Moving target tracking has always been an important research direction in machine vision. Based on the careful study of the compression tracking algorithm, this paper proposes an improved algorithm for collecting a large number of samples in the tracking phase, using the positive and negative classifiers for judgment and large computational complexity: In the previous frame tracking result of the video, the window with the larger cross-correlation value of the target frame is used as the optimal tracking position in the corresponding region of the current frame, thereby reducing the calculation amount. The results of computer simulation experiments show that the algorithm improves the operation speed without affecting the tracking accuracy.

关键词： Target tracking Image coding Feature extraction Classification algorithms Bayes methods signal processing algorithms Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

14th international conference on Pattern Recognition and Information processing, PRIP 2019

14th International conference on Pattern Recognition and Inf...

引用

14th international conference on Pattern Recognition and Information processing, PRIP 2019

ISBN: (纸本)9783030354299

The proceedings contain 25 papers. The special focus in this conference is on Pattern Recognition and Information processing. The topics include: Brands and Caps Labeling Recognition in Images Using Deep learning;influence of Control Parameters and the Size of Biomedical Image Datasets on the Success of Adversarial Attacks;performance of Sequential Tests for Random Data Monitoring Under Distortion;equipment Condition Identification Based on Telemetry signal Clustering;robots’ Vision Humanization Through machine-learning Based Artificial Visual Attention;automatic Analysis of Moving Particles by Total Internal Reflection Fluorescence Microscopy;fuzzy Morphological Filters for processing of Printed Circuit Board Images;Detection of Bulbar Dysfunction in ALS Patients Based on Running Speech Test;thresholding Neural Network Image Enhancement Based on 2-D Non-separable Quaternionic Filter Bank;method of Creating the 3D Face Model of Character Based on Textures Maps Module;shadow Detection in Satellite Images by Computing Its Characteristics;nearest Convex Hull Classifier with Simplified Proximity Measurement;image Semantic Segmentation Based on Convolutional Neural Networks for Monitoring Agricultural Vegetation;reliability Analysis Based on Incompletely Specified Data;semantic-Based Linguistic Platform for Big Data processing;cell Nuclei Counting and Segmentation for Histological Image Analysis;robust Person Tracking Algorithm Based on Convolutional Neural Network for Indoor Video Surveillance Systems;modeling of Intelligent Systems Architecture Based on the Brain Topology;temporal Convolutional and Recurrent Networks for Image Captioning;Video-Based Content Extraction Algorithm from Bank Cards for iOS Mobile Devices;FPGA Based Arbiter Physical Unclonable Function Implementation with Reduced Hardware Overhead;preface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OnkoGan: Bangla Handwritten Digit Generation with Deep Convolutional Generative Adversarial Networks 2nd

OnkoGan: Bangla Handwritten Digit Generation with Deep Convo...

引用

2nd international conference on Recent Trends in Image processing and Pattern Recognition, RTIP2R 2018

作者： Haque, Sadeka Shahinoor, Shammi Akter Rabby, A K M Shahariar Azad Abujar, Sheikh Hossain, Sayed Akhter Department of Computer Science and Engineering Daffodil International University Dhanmondi Dhaka1205 Bangladesh

ISBN: (纸本)9789811391866

From a very early age human achieve a precious skill that is a handwriting. After this invention, the ardor of it changed day by day. And every human has a different style of handwriting. So, facsimile anyone’s handwriting is a difficult task and it needs the strong ability of brain and practice. This paper is about this mimicry where an artificial system will do this by using Generative Adversarial Networks (GANs) [1]. GANs used in unsupervised machine learning that is implemented by two neural networks. GANs has a generator which generates fake images and a discriminator which make a difference between a real image and a fake image. We trained our proposed DCGAN [2] (Deep convolutional generative adversarial networks) to achieve our goal by using the three most popular Bangla handwritten datasets CMATERdb [3], BanglaLekha-Isolated [4], ISI [5] and our own dataset Ekush [6]. The proposed DCGAN successfully generate Bangla digits which makes it a robust model to generate Bangla handwritten digits from random noise. All code and datasets are freely available on https://***/SadekaHaque/BanglaGan. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

2nd international conference on Microelectronics, Computing and Communication Systems, MCCS 2017

2nd International Conference on Microelectronics, Computing ...

引用

2nd international conference on Microelectronics, Computing and Communication Systems, MCCS 2017

ISBN: (纸本)9789811082337

The proceedings contain 67 papers. The special focus in this conference is on Microelectronics, Computing and Communication Systems. The topics include: Thunderstorm prediction using soft computing and wavelet;Design of RFID tag antenna with impedance matching techniques at UHF band;decision tree and genetic algorithm based intrusion detection system;a novel method of image denoising using nonlocal algorithm;a novel multimedia encryption and decryption technique using binary tree traversal;ZC-CDTA based integrator circuit using single passive component;road and traffic sign detection using colour segmentation;trimmed median filter for removal of noise from medical image;Characterization of interfering signal in S band of IRNSS;analysis of voltage source boost inverter;Enhancing multibiometric system security using ECC based on score level fusion;generation of photographic mosaic using apache spark and scalding for image processing;mitigation of congestion in transmission line using series smart wire;mobility aware distributed clustering and routing algorithm based on A* search for mobile ad hoc networks;floating admittance matrix approach to model development of active devices and circuits;an efficient approach for monuments image retrieval using multi-visual descriptors;Comparison of ANN-based MPPT controller and incremental conductance for photovoltaic system;Low power implementation of 32-bit RISC processor with pipelining;A novel SINR-based cooperative radio resource allocation mechanism (SBC-RRAM) for LTE/Wi-Fi radio access system in smart home environment;optimal location of thyristor controlled series compensator to assuage congestion in transmission network;a study on filter design aspects of single-phase inverter with various modulation schemes;energy-efficient 64-bit asynchrobatic adder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using embedding-based metrics to expedite patients recruitment process for clinical trials 2

Using embedding-based metrics to expedite patients recruitme...

引用

2nd international conference on Big Data and Cyber-Security Intelligence, BDCSIntell 2019

作者： Dhayne, Houssein Kilany, Rima Faculty of Engineering ESIB Saint Joseph University Beirut Lebanon

—Despite the unprecedented volumes of Electronic Medical Records (EMRs) generated daily across healthcare facilities, the ability to leverage these data for patient participation in clinical trial remains overwhelmingly unfulfilled. The reason behind this is that matching patient information to the eligibility criteria for clinical trials is a manual, effort-consuming process. Therefore, automating this process is an essential step in improving the number of patients participating in clinical research. To address this issue, we propose a novel framework for automated patients to clinical trials matching. The matching process is based on measuring the similarity score between phrases extracted from patient medical records and the eligibility criterion for a trial. Our solution is based on a combination of NLP techniques and modern deep learning-based NLP models. In this context, we follow pre-training and transfer learning approaches to help the model learn task-specific reasoning skills. Additionally, we perform supervised fine-tuning on large Medical Natural Language Inference (MedNLI) and Semantic Textual Similarity (STS-B) datasets. The matching process was performed at semantic phrases level by converting patient information and trial criteria into vector representations. We then used a scoring function that combined cosine similarity and scaling normalization to identify potential patient-trial matches. The experimental results have shown that our framework is highly effective in sorting out patients by their similarity scores. Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 international (CC BY 4.0).

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Flux Bands Constricting Arc Ultra-narrow Gap Welding signal Characteristics that Used for Weld Tracking 2019

Flux Bands Constricting Arc Ultra-narrow Gap Welding Signal ...

引用

proceedings of the 2019 The 2nd international conference on Robotics, Control and Automation Engineering

作者： Wang Lei Qiao Jisen Chen Jianhong Lanzhou University of Technology State Key Laboratory of Advanced Processing and Recycling of Nonferrous Metals Lanzhou Gansu China

ISBN: (纸本)9781450376228

For solving the problem of automated robot ultra-narrow gap welding, based on flux bands constricting arc ultra-narrow gap welding experiments, a robot ultra-narrow gap welding system and real-time arc signal acquisition system were established. The paper elaborates the effect of robot kinematic accuracy on the welding process, and through studying the arc signal in different groove types and with different welding wire position in the groove to put forward an arc characteristic that can be used for weld tracking in ultra-narrow gap welding. Results of this study indicate that robot kinematic accuracy should be controlled less than ±1mm in flux bands constricting arc ultra-narrow gap welding. The narrower the groove gap is, the higher the requirement of robot kinematic accuracy is. As the welding torch deviation distance from center of groove increase, the arcing voltage is significantly reduced, the voltage drop is also reduced, but the peak current and short-circuit transition frequency are significantly increased. The arc signal reflects the arc state and welding wire position in the groove. The difference in the arc signal when the welding torch is near to and away from the side-wall, which can be used to track the center of the groove.

关键词： Ultra-narrow gap welding welding robot kinematic accuracy weld tracking arc signal characteristics

来源：评论

学校读者我要写书评

暂无评论

Automatic Feature Extraction for Vietnamese Sign Language Recognition using Support Vector machine 2

Automatic Feature Extraction for Vietnamese Sign Language Re...

引用

2nd international conference on Recent Advances in signal processing, Telecommunications and Computing (SigTelCom)

作者： Pham The Hai Huynh Chau Thinh Bui Van Phuc Ha Hoang Kha Ho Chi Minh City Univ Technol VNU HCM Fac Elect & Elect Engn Ho Chi Minh City Vietnam

ISBN: (纸本)9781538629765

This paper aims at finding an automatic approach for extracting features of the Vietnamese sign language to classify both static Vietnamese alphabet letters and their combing diacritic marks as dynamic hand gestures. A Vietnamese sign language recognition system (VSLRS) collects all images including depth images, RGB images, and skeletal join maps to extract the desired features of each hand gesture and their own movements. These characteristics are normalized and converted to build a full Vietnamese sign language combing diacritic marks. The primary features of this system are automatically extracting the hand gestures of the observed person before the Kinect device version 1, and both dynamic and static diacritic marks are able to be recognized because of the movement detection method. Multiclass support vector machines (SVMs) and the One-Against-All approach are employed to find two suitable SVMs for static and dynamic hand gesture recognition. During the recognition phase, all hand gestures are extracted, normalized, and then filtered out based on the Euclidean distance difference of hand positions in captured frames to go through the exact SVMs. The recognized letter or diacritic is the positive label of all the SVM classes. The experimental results demonstrate the proposed VSLRS recognized the Vietnamese sign language (VSL) in realtime with the high accuracy.

关键词： Support Vector machine one-against-all hand gesture extraction machine learning

来源：评论

学校读者我要写书评

暂无评论

Meteorite Hunting Using Deep learning and UAVs

Meteorite Hunting Using Deep Learning and UAVs

引用

international conference on signal processing and Information Security (ICSPIS)

作者： Aisha AlOwais Safa Naseem Takwa Dawdi Mariam Abdisalam Yusra Elkalyoubi Anas Adwan Khawla Hassan Ilias Fernini Sharjah Academy for Astronomy Space Sciences and Technology University of Sharjah Sharjah UAE

ISBN: (数字)9781728138732

ISBN: (纸本)9781728138749

In this paper, we present an automated meteorite detection system that employs an autonomous Unmanned Aerial Vehicle (UAV). It is programmed to recognize and locate meteorites using machine learning. In this design, the UAV carries a Single Board Computer (SBC), through which realtime data processing of the live video feed from an optical camera is performed. The integration of a GPS module into the system enables localization of the detected meteorites. The onboard processing, carried out by the SBC, involves analyzing each frame from the video and running it through our deep learning model. This model is trained on images of different types of commonly found meteorites, via Transfer learning performed on Convolutional Neural Networks (CNN). The results were promising, with an accuracy of approximately 90%. Future enhancements, including the addition of an infrared sensor to capture thermal images, are also discussed.

关键词： Training Cameras Deep learning Drones Hardware Rocks

来源：评论

学校读者我要写书评

暂无评论

Deep learning for Low-Field to High-Field MR: Image Quality Transfer with Probabilistic Decimation Simulator 2nd

Deep Learning for Low-Field to High-Field MR: Image Quality ...

引用

2nd international Workshop on machine learning for Medical Image Reconstruction (MLMIR) as part of the 22nd Medical Image Computing and Computer Assisted Intervention (MICCAI) conference

作者： Lin, Hongxiang Figini, Matteo Tanno, Ryutaro Blumberg, Stefano B. Kaden, Enrico Ogbole, Godwin Brown, Biobele J. D'Arco, Felice Carmichael, David W. Lagunju, Ikeoluwa Cross, Helen J. Fernandez-Reyes, Delmiro Alexander, Daniel C. UCL Ctr Med Image Comp London England UCL Dept Comp Sci London England Microsoft Res Cambridge Machine Intelligence & Percept Grp Cambridge England Univ Ibadan Dept Radiol Coll Med Ibadan Nigeria Univ Ibadan Dept Paediat Coll Med Ibadan Nigeria Great Ormond St Hosp Sick Children London England UCL Great Ormond St Inst Child Hlth London England Kings Coll London Dept Biomed Engn London England

ISBN: (纸本)9783030338435;9783030338428

MR images scanned at low magnetic field (<1T) have lower resolution in the slice direction and lower contrast, due to a relatively small signal-to-noise ratio (SNR) than those from high field (typically 1.5T and 3T). We adapt the recent idea of Image Quality Transfer (IQT) to enhance very low-field structural images aiming to estimate the resolution, spatial coverage, and contrast of high-field images. Analogous to many learning-based image enhancement techniques, IQT generates training data from high-field scans alone by simulating low-field images through a pre-defined decimation model. However, the ground truth decimation model is not well-known in practice, and lack of its specification can bias the trained model, aggravating performance on the real low-field scans. In this paper we propose a probabilistic decimation simulator to improve robustness of model training. It is used to generate and augment various low-field images whose parameters are random variables and sampled from an empirical distribution related to tissue-specific SNR on a 0.36T scanner. The probabilistic decimation simulator is model-agnostic, that is, it can be used with any super-resolution networks. Furthermore we propose a variant of U-Net architecture to improve its learning performance. We show promising qualitative results from clinical low-field images confirming the strong efficacy of IQT in an important new application area: epilepsy diagnosis in sub-Saharan Africa where only low-field scanners are normally available.

关键词： Image quality

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135页 << < 106 107 108 109 110 111 112 113 114 115 > >>

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：