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

472 篇 会议
15 篇 期刊文献

馆藏范围

487 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

369 篇 工学
- 173 篇 电气工程
- 162 篇 计算机科学与技术...
- 128 篇 信息与通信工程
- 100 篇 软件工程
- 44 篇 测绘科学与技术
- 27 篇 控制科学与工程
- 23 篇 电子科学与技术（可...
- 22 篇 仪器科学与技术
- 16 篇 生物医学工程（可授...
- 14 篇 机械工程
- 12 篇 光学工程
- 10 篇 生物工程
- 7 篇 化学工程与技术
- 6 篇 安全科学与工程
- 5 篇 水利工程
- 5 篇 航空宇航科学与技...
- 3 篇 材料科学与工程（可...
139 篇 理学
- 84 篇 物理学
- 35 篇 数学
- 14 篇 系统科学
- 11 篇 统计学（可授理学、...
- 10 篇 化学
- 10 篇 生物学
- 3 篇 地球物理学
105 篇 医学
- 102 篇 临床医学
- 5 篇 基础医学(可授医学...
- 5 篇 特种医学
19 篇 管理学
- 11 篇 图书情报与档案管...
- 9 篇 管理科学与工程(可...
3 篇 法学
- 3 篇 社会学
1 篇 经济学
1 篇 农学

主题

36 篇 target tracking
34 篇 signal processin...
32 篇 signal to noise ...
27 篇 signal processin...
26 篇 sensors
22 篇 data association
22 篇 radar
21 篇 target detection
18 篇 data fusion
18 篇 detection and tr...
14 篇 object detection
14 篇 multiple target ...
13 篇 training
12 篇 filtering (signa...
12 篇 estimation
12 篇 particle filters
11 篇 filtering
11 篇 tracking
11 篇 feature extracti...
11 篇 bayesian methods

机构

8 篇 cyberrnd inc cul...
7 篇 univ calif san d...
7 篇 univ connecticut...
4 篇 univ connecticut...
3 篇 qinetiq ltd malv...
3 篇 nanjing research...
3 篇 mcmaster univ de...
3 篇 numerica corp ft...
3 篇 numerica corp lo...
3 篇 usn ctr surface ...
3 篇 national key lab...
3 篇 univ connecticut...
2 篇 chus sherbrooke ...
2 篇 univ sherbrooke ...
2 篇 lockheed martin ...
2 篇 beihang univ sch...
2 篇 cub def applicat...
2 篇 univ melbourne d...
2 篇 leonardo uk edin...
2 篇 thales nederland...

作者

12 篇 kirubarajan t
11 篇 bar-shalom y
8 篇 kirubarajan t.
7 篇 bar-shalom yaako...
6 篇 blair wd
6 篇 sinha a
5 篇 willett peter
5 篇 drummond oliver ...
4 篇 sworder dd
4 篇 maskell s
4 篇 drummond oe
4 篇 danford scott
4 篇 boyd je
4 篇 willett p
3 篇 blair w. dale
3 篇 gray je
3 篇 kragel bret d.
3 篇 sinha a.
3 篇 hernandez ml
3 篇 lim et

语言

479 篇 英文
4 篇 中文
3 篇 土耳其文
1 篇 其他

检索条件"任意字段=16th Conference on Signal and Data Processing of Small Targets"

共 487 条记录，以下是151-160 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：

Unambiguous Determination of Oscillation Frequency for Multiple Objects using Quadrature Doppler Radar 30

Unambiguous Determination of Oscillation Frequency for Multi...

引用

Asia-Pacific Microwave conference (APMC)

作者： Whitworth, Avon Ishmael, Khaldoon Yavari, Ehsan Boric-Lubecke, Olga Univ Hawaii Dept Elect Engn Holmes Hall 4832540 Dole St Honolulu HI 96822 USA Adnov LLC 2800 Woodlawn DrSuite 297 Honolulu HI 96822 USA

ISBN: (纸本)9784902339451

Doppler radar can potentially be used to detect respiration and heart rates of human subjects without the inconvenience of attaching transducers to the subjects. We simulated breathing rates of two subjects with two oscillating targets, and recorded the resulting data received when the targets are subject to a continuous wave signal transmitted by a 2.4GHz quadrature channel receiver. Using small changes in the initial center position of one target which passed through the null and optimum positions in the I and Q channels, and then applying a Fast Fourier Transform, we demonstrated that it is possible to remotely distinguish the oscillation frequency of each target.

关键词： Biomedical signal detection biomedical signal processing Doppler radar frequency measurement Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

A Fast Algorithm of GNSS-R signal processing Based on DBZP 8th

A Fast Algorithm of GNSS-R Signal Processing Based on DBZP

引用

8th China Satellite Navigation conference (CSNC)

作者： Han, Lin Meng, Yansong Wang, Yanguang Han, Xingyuan Acad Space Elect Informat Technol Inst Satellite Nav & ISL Technol Xian 710100 Shaanxi Peoples R China

ISBN: (纸本)9789811045882;9789811045875

An important observation of GNSS-R is Delay-Doppler mapping (DDM). According to the requirement of GNSS-R signal real-time processing, a fast processing algorithm of GNSS-R signal based on double block zero padding (DBZP) and frequency domain rotation transformation is proposed for DDM generation. the reflected data is blocked and then correlated, which avoids the FFT calculation with too long points. the block and zero padding operations not only guarantee the full search of the pseudo code phase, but also avoid the repetitive calculation. In the frequency domain, the correlation results at different Doppler frequencies are approximated by the rotation transformation method, which avoids a large number of carrier multiplication operations and effectively reduces the computational burden. the computational burden and computational loss of parallel code phase correlation algorithm and fast algorithm are analyzed. Finally, the UK-DMC satellite-borne reflected data are processed by two algorithms and the simulation time-consuming and processing results were compared. the results show that the fast algorithm greatly shortens the DDM generation time and the loss of the processing result is small.

关键词： GNSS-R GNSS reflected signal processing DBZP Fast algorithm DDM

来源：评论

学校读者我要写书评

暂无评论

TRANSFERRING CNNS TO MULTI-INSTANCE MULTI-LABEL CLASSIFICATION ON small dataSETS 24

TRANSFERRING CNNS TO MULTI-INSTANCE MULTI-LABEL CLASSIFICATI...

引用

24th IEEE International conference on Image processing (ICIP)

作者： Dong, Mingzhi Pang, Kunkun Wu, Yang Xue, Jing-Hao Hospedales, Timothy Ogasawara, Tsukasa UCL London England Univ Edinburgh Edinburgh Midlothian Scotland Nara Inst Sci & Technol Ikoma Japan

ISBN: (纸本)9781509021758

Image tagging is a well known challenge in image processing. It is typically addressed through multi-instance multi-label (MIME) classification methodologies. Convolutional Neural Networks (CNNs) possess great potential to perform well on MIML tasks, since multi-level convolution and max pooling coincide with the multi-instance setting and the sharing of hidden representation may benefit multi-label modeling. However, CNNs usually require a large amount of carefully labeled data for training, which is hard to obtain in many real applications. In this paper, we propose a new approach for transferring pre-trained deep networks such as VGG16 on lmagenet to small MIML tasks. We extract features from each group of the network layers and apply multiple binary classifiers to them for multi-label prediction. Moreover, we adopt an L-1-norm regularized Logistic Regression (L1LR) to find the most effective features for learning the multi-label classifiers. the experiment results on two most-widely used and relatively small benchmark MIML image datasets demonstrate that the proposed approach can substantially outperform the state-of-the-art algorithms, in terms of all popular performance metrics.

关键词： CNN Multi-instance Multi-label small dataset Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Kalman Filter for Tracking of Fast Accelerating targets 14

Adaptive Kalman Filter for Tracking of Fast Accelerating Tar...

引用

14th European Radar conference (EURAD)

作者： Hudec, Premysl Panek, Petr Czech Tech Univ Fac Elect Engn Dept Electromagnet Field Tech 2 Prague 16627 6 Czech Republic Acad Sci Czech Republ Inst Photon & Elect Chaberska 57 Prague 8 Czech Republic

ISBN: (纸本)9782874870491

Active defense (AD) is a new method for protecting military vehicles. Instead of using thick and extremely heavy armors, the actively protected vehicles monitor approaching threatening missiles and de-active them by a suitable active counter-measures. the majority of AD systems is based on radar sensors capable of detecting the concerned missiles and measuring their parameters important for the protective functions. Often, these radar sensors are required to operate in a near-zone (from zero to tens of meters) and find and track relatively small and fast-flying targets. Beside that, it is necessary to take into account the fact that the velocity of the monitored targets can instantaneously vary. this problem especially refers to ignition of rocket engines which can abruptly introduce extremely high accelerations. If the concerned radar sensors employ signal-processing methods based on Kalman filtration, these high-order time-derivatives can cause substantial convergence problems. the main purpose of this article is to present the newly developed adaptable filtering which can reduce these effects. the designed procedures were verified using practically recorded data from flight of RPG-7 missiles.

关键词： Kalman filtration adaptive filtration radar sensor pseudo-noise CW radar

来源：评论

学校读者我要写书评

暂无评论

On the use of deep neural networks for the detection of small vehicles in ortho-images 24

On the use of deep neural networks for the detection of smal...

引用

24th IEEE International conference on Image processing, ICIP 2017

作者： Terrail, Jean Ogier Du Jurie, Frederic Safran Electronics and Defense Normandie Univ UNICAEN ENSICAEN CNRS France Normandie Univ UNICAEN ENSICAEN CNRS France

ISBN: (纸本)9781509021758

this paper addresses the question of the detection of small targets (vehicles) in ortho-images. this question differs from the general task of detecting objects in images by several aspects. First, the vehicles to be detected are small, typically smaller than 20×20 pixels. Second, due to the multifarious-ness of the landscapes of the earth, several pixel structures similar to that of a vehicle might emerge (roof tops, shadow patterns, rocks, buildings), whereas within the vehicle class the inter-class variability is limited as they all look alike from afar. Finally, the imbalance between the vehicles and the rest of the picture is enormous in most cases. Specifically, this paper is focused on the detection tasks introduced by the VEDAI dataset [1]. this work supports an extensive study of the problems one might face when applying deep neural networks with low resolution and scarce data and proposes some solutions. One of the contributions of this paper is a network severely outperforming the state-of-the-art while being much simpler to implement and a lot faster than competitive approaches. We also list the limitations of this approach and provide several new ideas to further improve our results. © 2017 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

theoretical substantiation of the rock outburst criterion in terms of amplitude-frequency characteristics of an acoustic signal 16

Theoretical substantiation of the rock outburst criterion in...

引用

16th International conference Geoinformatics: theoretical and Applied Aspects

作者： Sdvyzhkova, O. Golovko, Yu. Klimenko, D. National Mining University Ukraine

ISBN: (纸本)9789462822207

the purpose of research. Deriving the criterion of a crack (joint) initiating under simultaneous effect of the rock stress state and elastic oscillations generated by an external source is a research purpose. Determining the quantitative relations to estimate the contribution of oscillations in crack initiation and create a theoretical basis for the improvement of rock burst forecasting technique is a goal as well. Methods. the brittle failure theory and a time-space approach are applied to determine a critical length of initiating cracks depending on stress level and amplitude-frequency characteristics of acoustic oscillations. Analysis of experimental data and comparison with the numerical results is carried out. Findings. Quantitative ratios between a critical length of the crack, a stress intensity factor, oscillation amplitude and a frequency are determined. It is shown that there are such values of the oscillation frequencies at which the critical crack length is especially sensitive relatively the amplitude alteration. the increase in the oscillation amplitude initiates starting the crack with small length. Numerical estimation is made for close-grained sandstone using such characteristics as crack resistance factor and Rayleigh' wave velocity and tensile strength. Increasing the amplitude twice at the frequency of 1145Hz causes the reduction of starting crack length 3 times. Numerical results correlate with in situ data related to acoustic predicting the dynamic phenomena in the rock mass. Originality. the crack initiation criterion has been identified. Practical implications. Quantitative relations between stress components and amplitude-frequency characteristics should be used to improve the outburst forecasting technique and increase the reliability of dynamic effect prediction.

关键词： Rock bursts

来源：评论

学校读者我要写书评

暂无评论

Supervised Semi-Autoencoder Learning for Multi-Layered Neural Networks 17

Supervised Semi-Autoencoder Learning for Multi-Layered Neura...

引用

Joint 17th World Congress of International-Fuzzy-Systems-Association / 9th International conference on Soft Computing and Intelligent Systems (IFSA-SCIS)

作者： Kamimura, Ryotaro Takeuchi, Haruhiko Tokai Univ IT Educ Ctr 4-1-1 Kitakaname Hiratsuka Kanagawa 2591292 Japan Natl Inst Adv Ind Sci & Technol Human Informat Res Inst 1-1-1 Higashi Tsukuba Ibaraki 3058566 Japan

ISBN: (纸本)9781509049172

the present paper proposes a new type of layer-wise learning for multi-layered neural networks. Multi-layered neural networks have the serious problem of vanishing information, where information contained in input patterns is gradually lost, and preventing neural networks from learning input patterns. In particular, the autoencoders used in the greedy layer-wise pre-training tend to lose the original information by going through multiple layers. For this problem, we propose a new approach called "supervised semi-autoencoder" to solve the problem of vanishing information. the new method is close to the ordinary autoencoder, but the outputs are the original inputs and the corresponding targets for amplifying information in input patterns. In addition, the computational procedures are simplified by using potential learning, in which the potentiality of neurons is determined before learning, and is given as initial weights. thus, the complicated adjustment of parameters is not necessary. the method was applied to the well-known crab data set as well as the real data set of eye-tracking records. In both cases, with relatively small-sized data, neural networks could find internal representations close to those obtained by larger ones, and better generalization performance could be observed.

关键词： Estimation Field programmable gate arrays OFDM Modulation Filtration Clocks signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Motion-oriented Noisy Physiological signal Refining Using Embedded Sensing Platforms 39

Motion-oriented Noisy Physiological Signal Refining Using Em...

引用

39th Annual International conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Park, Jaeyeon Nam, Woojin Kim, Tae Young Lee, Sukhoon Yoon, Dukyong Ko, JeongGil Ajou Univ Dept Comp Engn Suwon South Korea Ajou Univ Sch Med Dept Biomed Informat Suwon South Korea

ISBN: (纸本)9781509028092

Recent improvements in data learning techniques have catalyzed the development of various clinical learning systems. However, for clinical applications, training from noisy data can cause significant misleading results, directly leading to potentially dangerous clinical decisions. Given its importance, this work targets to present a preliminary effort to identify corrupted vital sign data by analyzing the patient motions on hospital beds. Specifically, we design an embedded sensor-based motion detection platform to capture and categorize different noise-causing motion on intensive care unit beds through a pre-deployment study at the Ajou University Hospital. We design light-weight and low-resource demanding software for motion sensor data processing and evaluate its performance from real-patient traces collected at the ICU. Evaluation results using a similar to 200 minute data set show that our system detects and classifies patient motion states with 76% accuracy and well-identifies vital sign time-series regions affected by motion noise.

关键词： Gyroscopes Physiology Sensors Biomedical monitoring Accelerometers Classification algorithms Training

来源：评论

学校读者我要写书评

暂无评论

3D Morphable Models as Spatial Transformer Networks 16

3D Morphable Models as Spatial Transformer Networks

引用

16th IEEE International conference on Computer Vision (ICCV)

作者： Bas, Anil Huber, Patrik Smith, William A. P. Awais, Muhammad Kittler, Josef Univ York Dept Comp Sci York N Yorkshire England Univ Surrey Ctr Vis Speech & Signal Proc Guildford Surrey England

ISBN: (纸本)9781538610343

In this paper, we show how a 3D Morphable Model (i.e. a statistical model of the 3D shape of a class of objects such as faces) can be used to spatially transform input data as a module (a 3DMM-STN) within a convolutional neural network. this is an extension of the original spatial transformer network in that we are able to interpret and normalise 3D pose changes and self-occlusions. the trained localisation part of the network is independently useful since it learns to fit a 3D morphable model to a single image. We show that the localiser can be trained using only simple geometric loss functions on a relatively small dataset yet is able to perform robust normalisation on highly uncontrolled images including occlusion, self-occlusion and large pose changes.

关键词： three-dimensional displays Shape Solid modeling Two dimensional displays Computational modeling Training Geometry

来源：评论

学校读者我要写书评

暂无评论

Fast and Robust GPS Fix Using One Millisecond of data

Fast and Robust GPS Fix Using One Millisecond of Data

引用

International Symposium on Information processing in Sensor Networks (IPSN)

作者： Pascal Bissig Manuel Eichelberger Roger Wattenhofer ETH Zurich

ISBN: (纸本)9781467391474

GPS is used for outdoor localization in a large variety of applications. Current receivers consume too much power for energy-constrained situations like continuous location tracking on small wearable devices. Mainly, this is due to the large amount of GPS signal that has to be decoded to compute the first position fix. While Coarse-Time Navigation (CTN) can reduce the necessary signal to a few milliseconds, it is not robust to noise. Collective Detection (CD) of satellites can mitigate noise to some degree, but the basic method is computationally expensive. We show how CD can be solved optimally and emciently. Furthermore, we improve the accuracy of CD by exploiting the shape of the likelihood function. All our results are based on real-world signal observations and we achieve localization accuracies of less than 25 meters using a single millisecond of signal. When using 10 consecutive millisecond samples the accuracy improves to less than 10 meters.

关键词： Receivers Global Positioning System Satellites Satellite broadcasting Robustness Meters

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49页 << < 12 13 14 15 16 17 18 19 20 21 > >>

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：