检索结果-内蒙古大学图书馆

2017 5th International conference on Mechanical, Automotive and Materials Engineering（CMAME 2017）

作者： Gong Weiming Zhao Ming Ge Xinfeng Ding Yongsheng Du Jinqi Zhang Yizhong Jiangdu water conservancy project administrative office of Jiangsu Province Research Institute of Yunnan Power Grid Co.Ltd. College of Energy and Electric Engineering Hohai University Yunnan Electric Test&Research Institute Group CO.LTD Yunnan Electric Test&Research Institute GROUP CO.LTD Hunan electric power research institute of State Grid

this paper uses NI Compact RIO hardware platform,the CRIO has a small,convenient and suitable for harsh *** on Labview software platform,developed vibration condition monitor data acquisition and processing system,using the FPGA module and real-time processing module,realized high accuracy real-time and high sampling rate,and through wavelet analysis,processing the collected the *** to the time-frequency characteristics of the wavelet analysis,the analysis of singularity of the fault signal has more advantages than the traditional spectrum *** the wavelet analysis,vibration Compact RIO system can accurate extraction of fault feature of vibration unit..

关键词： Compact RIO data Acquisition Hydro Turbine Condition monitoring Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

A New Method to Parallel Implementation for Batching Vast small-scale Computing Tasks Based on GPU 11

A New Method to Parallel Implementation for Batching Vast Sm...

引用

IEEE 11th conference on Industrial Electronics and Applications (ICIEA)

作者： Zhu, Jun Yao, Haifeng Yang, Tao Zhou, Qiaomei Li, Kai Anhui Univ Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei Peoples R China Shanghai Res Ctr Wireless Commun Technol & Innovat Dept Shanghai Peoples R China

ISBN: (纸本)9781467386449

the calculation of small-scale data is commonly used in scientific computing and application domain, and the high-efficiency method of small calculation can give play to the potency of many calculation and application. In this paper, a novel self-adaptive parallel computing method based on the graphics processing unit ( GPU) architecture for batches of small scale computing tasks is proposed herein. It also provides two other implementation methods, which are the CPU algorithm and the traditional GPU algorithm, and then compares the efficiency of the three schemes. the experimental results show that the implementation efficiency of this new method on the GPU is better than that of method executed by the CPU and that of the traditional GPU algorithm for batching small-scale computing tasks. And this new approach is furthest utilizing the GPU resources, while a large amount of data is processed.

关键词： small-scale GPU batch processing adaptation parallel

来源：评论

学校读者我要写书评

暂无评论

A high power EMI sensor for detecting and classifying small and deep targets 21

A high power EMI sensor for detecting and classifying small ...

引用

conference on Detection and Sensing of Mines, Explosive Objects, and Obscured targets XXI

作者： Shubitidze, F. Barrowes, B. E. Wang, Yinlin Shamatava, Irma Sigman, J. B. O'Neill, K. Steinhurst, Daniel A. Dartmouth Coll Thayer Sch Engn HB 8000 Hanover NH 03755 USA White River Technol Inc 3 Schoolhouse Ln Etna NH 03750 USA USA ERDC Cold Reg Res & Engn Lab Hanover NH 03755 USA Nova Res Inc Alexandria VA 22308 USA

ISBN: (纸本)9781510600645

Detecting and classifying small (i.e., with calibers ranging from 20 to 60 mm) and deep targets (burial depth more than 11 times targets diameter) is still a challenging problem using current advanced EMI sensors and signal processing approaches. In order to overcome this problem, the standard time-domain NRL TEMTADS 2x2 electromagnetic induction (EMI) instrument is updated. Namely, the NRL TEMTADS 2x2 system's transmitter electronics is modified to increase transmitter (Tx) currents from 6 Amperes to 14 Amperes. the instrument has a Tx array with four coplanar square coils, together with four tri-axial receivers (Rx) placed at the center of each Tx. Each Rx cube contains three orthogonal coils and thus registers all three vector components of the impinging signals. the Tx coils, with transmitter currents of similar to 14 A, illuminate a buried target, and the target responses are collected with a 500 kHz sample rate after turn off of the excitation pulse. the system operates in both static (cued) and dynamic modes. For cued mode, the raw decay measurements are grouped into 121 logarithmically-spaced " gates" whose center times range from 25 mu s to 24.35 ms with 5% widths. the sensor is placed on a cart which provides a sensor-to-ground offset of 20 cm or less. In this paper, studies for APG Calibration, Blind, and small Munitions Grids are presented and analyzed. the areas are arranged in grids of test cells and the cell center positions are known. Each target position is flagged with a non-metallic pin flag using cm-level GPS. the sensor is positioned over each target in turn. With the system positioned over the target, each Tx is activated sequentially and during off the Tx current, all four Rx record data. the capabilities of this sensor platform is rigorously investigated for UXO classification at APG blind and small munitions grids.

关键词： High Power detection classification UXO advanced models EMI Sensors ONVMS modeling APG test-site mini-Metal Mapper

来源：评论

学校读者我要写书评

暂无评论

Ultrawideband Inverse Scattering Method for Resonance Region Target Recognition: Application to small-Scale Airplane targets with Measured data 9

Ultrawideband Inverse Scattering Method for Resonance Region...

引用

9th European conference on Antennas and Propagation EuCAP

作者： Secmen, Mustafa Yasar Univ Dept Elect & Elect Engn Izmir Turkey

ISBN: (纸本)9788890701856

this paper develops an inverse scattering method to determine the characteristics of resonance region targets by using ultrawideband scattering signals. the method mainly uses multiple time-domain signals for each target, and they are processed to give feature vectors in frequency domain. these vectors contain target-specific information related with characteristics (dimensions of substructures, material properties, etc.) of the known targets. the target recognition is employed by using test (unknown) target's scattering signal. this time-domain signal is processed in an inverse way to get a frequency-domain test vector. then, the characteristics of test target are assigned as these of one of the known targets with a basic template-matching approach between test vector and feature vectors of these targets. the method is demonstrated for three realistic small-scale airplane. For an ultrawideband system of 0.7-18 GHz, more than 85 percent accuracy has been obtained even under moderate signal-to-noise (SNR) ratio of about 10 dB.

关键词： ultrawideband inverse scattering radar signal processing resonance region

来源：评论

学校读者我要写书评

暂无评论

Detection of infrared dim and small targets based on saliency and grayscale morphological reconstruction 34

Detection of infrared dim and small targets based on salienc...

引用

第三十四届中国控制会议

作者： GU Zhangyuan YANG Shuo LI Jianxun School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

ISBN: (纸本)9781467374439

Based on saliency and grayscale morphological reconstruction, a new detection algorithm for infrared dim and small targets is proposed in this paper. the saliency of the original image to obtain the region of interest(ROI) is analyzed, then the spatial domain characteristic of dim and small targets is introduced into the marker image. Grayscale morphological reconstruction is based on the marker image and the mask image(the original image). Because saliency efficiently concentrates the gradient difference of the targets, detection probability is improved also with little false alarms. As the role of recognition, spatial domain characteristic of target reduces false alarm probability with the same detection probability, and background can be well estimated by grayscale morphological reconstruction, after subtraction, dim and small targets are detected. Experiments of real data prove the better detection performance, especially higher signal-to-noise ratio(SNR).

关键词： Infrared dim and small targets,Saliency,Morphological reconstruction,Background estimation

来源：评论

学校读者我要写书评

暂无评论

Class Discovery via Bimodal Feature Selection in Unsupervised Settings 14

Class Discovery via Bimodal Feature Selection in Unsupervise...

引用

IEEE 14th International conference on Machine Learning and Applications ICMLA

作者： Curtis, Jessica Kon, Mark Boston Univ Dept Math & Stat Boston MA 02215 USA

ISBN: (纸本)9781509002870

In machine learning there are numerous supervised techniques that extend naturally to analogous unsupervised methods, such as clustering. In this paper, we consider so-called rare-weak models, in which the number of important features is small (or rare) and the signal strength of each important feature is minimal (or weak). When classical clustering is applied crudely in "big data" scenarios, significant problems can arise, including long computational run times and significant clustering errors. One solution is to use feature selection (FS) to reduce dataset dimensionality before clustering. We introduce two novel unsupervised feature selection methods, one parametric and one nonparametric, based on what we call bimodal feature selection. these methods produce ranked lists of features based on their univariate multi-modality. Unlike previously developed univariate FS methods, which have typically been restricted to 2-cluster scenarios, our method has been adapted and tested to discriminate binary and higher level clusterings. the method is particularly advantageous in rare-weak settings, since reducing data dimensionality allows classical clustering methods to be applied computationally faster and with greater accuracy.

关键词： Clustering Feature selection Unsupervised data

来源：评论

学校读者我要写书评

暂无评论

small TARGET OF SEA SURFACE DETECTION ALGORIthM RESEARCH BASED ON FEATURE CLASSIFICATION 12

SMALL TARGET OF SEA SURFACE DETECTION ALGORITHM RESEARCH BAS...

引用

12th IEEE International conference on signal processing (ICSP)

作者： Yu, Lianqing Li, Yun Wang, Ning Jiang, Jin Nanjing Res Inst Elect Technol Nanjing 210039 Jiangsu Peoples R China

ISBN: (纸本)9781479921867

this paper focuses on small target of sea surface detection in sea clutter. Firstly, it analyses the statistic of sea clutter. Secondly, three feature vectors (namely, RAA, RPH and RVE) are extracted, which is utilized to discriminate the sea clutter and targets, and then the time-Doppler curve is used to distinguish the multi-targets in order to finish the small target of sea surface detection. Finally, it analyses the trial data of some radar and shows that this algorithm can effectively distinguish the sea clutter and small target of sea surface. this paper provides a new approach for the ship-borne surveillance radar or marine radar to detect the small target of sea surface and antisubmarine warfare patrol.

关键词： Sea Cluttert Target Detection Feature Detection Feature Classification Time-Doppler Curve

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Compressed Sensing-Based LDA Topic Model for Polarimetric SAR Image Classification

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARth OBSERVATIONS AND REMOTE SENSING 2014年第3期7卷 972-982页

作者： He, Chu Zhuo, Tong Ou, Dan Liu, Ming Liao, MingSheng Wuhan Univ Sch Elect Informat Signal Proc Lab Wuhan 430072 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China

In this paper, a nonlinear compressed sensing-based LDA Topic (NCSLT) model is proposed for the classification of polarimetric synthetic aperture radar (PolSAR) images. the CS theory shows that when a signal is sparsely rendered on some basis, it can be recovered exactly by a relatively small set of random measurements of the original signal. In this paper, such notion is applied to a more general case to analyze nonlinear PolSAR data. therefore, the NCSLT model is presented with the following two objectives: 1) to capture the nonlinear structure of PolSAR data on a manifold surface using the CS theory and 2) to provide a generative explanation for the relationship between the image pixels and high-level complex scenes for image classification by establishing a Texture-CS-Topic model. Compared with the other traditional SAR image-classification methods, the proposed method displayed potential achievements when applied to two sets of PolSAR image data.

关键词： Image classification nonlinear compressed sensing-based LDA Topic (NCSLT) model polarimetric synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Wavelet-domain de-noising technique for thz pulsed spectroscopy 8

Wavelet-domain de-noising technique for THz pulsed spectrosc...

引用

8th conference of Optics and Photonics for Information processing

作者： Chernomyrdin, Nikita V. Zaytsev, Kirill I. Gavdush, Arsenii A. Fokina, Irina N. Karasik, Valeriy E. Reshetov, Igor V. Kudrin, Konstantin G. Nosov, Pavel A. Yurchenko, Stanislav O. Bauman Moscow State Tech Univ 2nd Baumanskaya Str 5 Moscow 105005 Russia Moscow Res Inst Oncol Moscow 125284 Russia

ISBN: (纸本)9781628412437

De-noising of terahertz (thz) pulsed spectroscopy (TPS) data is an essential problem, since a noise in the TPS system data prevents correct reconstruction of the sample spectral dielectric properties and to perform the sample internal structure studying. there are certain regions in TPS signal Fourier spectrum, where Fourier-domain signal-to-noise ratio is relatively small. Effective de-noising might potentially expand the range of spectrometer spectral sensitivity and reduce the time of waveform registration, which is an essential problem for biomedical applications of TPS. In this work, it is shown how the recent progress in signal processing in wavelet-domain could be used for TPS waveforms de-noising. It demonstrates the ability to perform effective de-noising of TPS data using the algorithm of the Fast Wavelet Transform (FWT). the results of the optimal wavelet basis selection and wavelet-domain thresholding technique selection are reported. Developed technique is implemented for reconstruction of in vivo healthy and deseased skin samplesspectral characteristics at thz frequency range.

关键词： terahertz technology terahertz pulsed spectroscopy wavelet-domain signal processing wavelet-domain de-noising biomedical applications

来源：评论

学校读者我要写书评

暂无评论

3D Shape Reconstruction from a Humanoid Generated Video Sequence 14

3D Shape Reconstruction from a Humanoid Generated Video Sequ...

引用

14th IEEE-RAS International conference on Humanoid Robots (Humanoids)

作者： Martinez, P. A. Varas, D. Castelan, M. Camacho, M. Marques, F. Arechavaleta, G. Inst Politecn Nacl Ctr Invest & Estud Avanzados Robot & Adv Mfg Grp Ramos Arizpe Coah Mexico Univ Politecn Cataluna Dept Signal Theory & Commun ES-08034 Barcelona Spain

ISBN: (纸本)9781479971749

this paper presents a strategy for estimating the geometry of an interest object from a monocular video sequence acquired by a walking humanoid robot. the problem is solved using a space carving algorithm, which relies on both the accurate extraction of the occluding boundaries of the object as well as the precise estimation of the camera pose for each video frame. For data acquisition, a monocular visual-based control has been developed that drives the trajectory of the robot around an object placed on a small table. Due to the stepping of the humanoid, the recorded sequence is contaminated with artefacts that affect the correct extraction of contours along the video frames. To overcome this issue, a method that assigns a fitness score for each frame is proposed, delivering a subset of camera poses and video frames that produce consistent 3D shape estimations of the objects used for experimental evaluation.

关键词： humanoid robots image reconstruction image sensors image sequences shape recognition 3D shape reconstruction humanoid generated video sequence monocular video sequence monocular visual-based control space carving algorithm walking humanoid robot Cameras Image reconstruction Robot vision systems Shape three-dimensional displays Trajectory Video sequences image reconstruction robot vision system three-dimensional displays Humanoid robots Cameras shape recognition Sensors (image) trajectory image sequences shape reconfiguration Pattern recognition 3D shape VIDEO FRAMES Humanoid

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：