中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共9条，第1-9条

帮助

条数/页：排序方式：
	A 2-D Long Short-Term Memory Fusion Networks for Bearing Remaining Useful Life Prediction 期刊论文 OAI收割 IEEE SENSORS JOURNAL, 2022, 卷号: 22, 期号: 22, 页码: 21806-21815 作者: Li, Yuan; Wang, Huanjie; Li, Jingwei; Tan, Jie \| 收藏 \| 浏览/下载：25/0 \| 提交时间：2023/03/20 Hidden Markov models Feature extraction Predictive models Sensors Mathematical models Data models Adaptation models 2-D long short-term memory (2D-LSTM) fault occurrence time (FOT) detection information fusion unit (IFU) remaining useful life (RUL) prediction
	Cross-model retrieval with deep learning for business application 会议论文 OAI收割 Busan, Korea, Republic of, 2020-11-14 作者: Wang, Yufei; Wang, Huanting; Yang, Jiating; Chen, Jianbo \| 收藏 \| 浏览/下载：30/0 \| 提交时间：2021/04/06 Cross-modal retrieval Audio features Deep hashing Useful information
	Study on time registration method for photoelectric theodolite data fusion (EI CONFERENCE) 会议论文 OAI收割 10th World Congress on Intelligent Control and Automation, WCICA 2012, July 6, 2012 - July 8, 2012, Beijing, China Yang H.-T.; Gao H.-B. 收藏 \| 浏览/下载：18/0 \| 提交时间：2013/03/25 In range measurement theodolite and radar constitute a real-time tracking system at different sites to track the same target in the air and get useful information exactly and timely. As the optical theodolite and radar have different sampling frequency and measurement system the data is sent to the fusion center is asynchronous. This paper proposed a time registration method based on multi-sensor data using Wavelet neural network algorithm which not only better solved the basic problems of theodolite fusion tracking but also improve the efficiency of data fusion. Simulation experiment and comparison with other time registration method have shown the advantage of this method. 2012 IEEE.
	Evaluation of spatial upscaling methods based on remote sensing data with multiple spatial resolutions (EI CONFERENCE) 会议论文 OAI收割 Satellite Data Compression, Communications, and Processing VIII, August 12, 2012 - August 13, 2012, San Diego, CA, United states Ren R.; Gu L.; Cao J.; Chen H.; Sun J. 收藏 \| 浏览/下载：28/0 \| 提交时间：2013/03/25 In most applications of remote sensing data special spatial information is required from a finer to a coarser spatial resolution with appropriate upscaling methods. The purpose of this paper is to compare and evaluate current spatial upscaling methods using MODIS remote sensing data with multiple spatial resolutions. In the research Northeast China was selected as the study area. MODIS data with spatial resolutions of 250 m (2 bands) and 500 m (7 bands) were used as the test data. Through using the selected upscaling methods the Band 1 and Band 2 data of MODIS were scaled up from 250 m to 500 m spatial resolution. On the basis of land cover characteristics of Northeast China the MODIS data located in the study area was classified into the five land cover types including water grasslands forests farmlands and bare lands using maximum likelihood method. The land cover classification results were further compared with MODIS Land Cover Type product. Finally Structural Similarity (SSIM) was selected to evaluate the effects of these upscaling methods. The research can provide more useful information for spatial scaling transformation in remote sensing data applications. 2012 SPIE.
	Information extraction from laser speckle patterns using wavelet entropy techniques (EI CONFERENCE) 会议论文 OAI收割 MIPPR 2011: Multispectral Image Acquisition, Processing, and Analysis, November 4, 2011 - November 6, 2011, Guilin, China 作者: Li X.-Z.; Wang X.-J. 收藏 \| 浏览/下载：37/0 \| 提交时间：2013/03/25 A novel speckle patterns processing method is presented using multi-scale wavelet techniques. Laser speckle patterns generated from the sample contained abundant information. In this paper we propose a method using wavelet entropy techniques to analyze the speckle patterns and exact the information on the sample surface. In our case we used this approach to test the solar silicon cell surface profiles based on the sym8 orthogonal wavelet family. According different wavelet entropy values the micro-structure of different solar silicon cell surfaces were comparative analyzed. Furthermore we studied the AFM and reflective spectra of the wafer. Results show that the wavelet entropy speckle processing method is effective and accurate. And the experiment proved that this method is a useful tool to investigate the surface profile quality. 2011 SPIE.
	Experimental analysis of accelerometer installation error (EI CONFERENCE) 会议论文 OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China Yanqiu H.; Juan C.; Peng Y. L. 收藏 \| 浏览/下载：16/0 \| 提交时间：2013/03/25 When accelerometer is installed errors would be produced which will greatly degrade the measurement accuracy so to the tracking precision while being applied in the compound control. We make the experimental analysis for the accelerometer installation in which the accelerometer is installed parallel to the azimuth and 30 degree away the azimuth. The data are dealt with and compared with the theoretical results. Out work can offer useful information for the calibration of accelerometer in the optoelectronic tracking system. 2010 IEEE.
	Assessment of surface roughness by use of soft x-ray scattering (EI CONFERENCE) 会议论文 OAI收割 Soft X-Ray Lasers and Applications VIII, August 4, 2009 - August 6, 2009, San Diego, CA, United states Yan-li M.; Yong-gang W.; Shu-yan C.; Bo C. 收藏 \| 浏览/下载：27/0 \| 提交时间：2013/03/25 A soft x-ray reflectometer with laser produced plasma source has been designed which can work from wavelength 8nm to 30 nm and has high performance. Using the soft x-ray reflectometer above the scattering light distribution of silicon and zerodur mirrors which have super-smooth surfaces could be measured at different incidence angle and different wavelength. The measurement when the incidence angle is 2 degree and the wavelength is 1 lnm has been given in this paper. A surface scattering theory of soft x-ray grazing incidence optics based on linear system theory and an inverse scattering mathematical model is introduced. The vector scattering theory of soft x-ray scattering also is stated in detail. The scattering data are analyzed by both the methods above respectively to give information about the surface profiles. On the other hand both the two samples are measured by WYKO surface profiler and the surface roughness of the silicon and zerodur mirror is 1.3 nm and 1.5nm respectively. The calculated results are in quantitative agreement with those measured by WYKO surface profiler which indicates that soft x-ray scattering is a very useful tool for the evaluation of highly polished surfaces. But there still some difference among the results of different theory and WYKO and the possible reasons of such difference have been discussed in detail. 2009 SPIE.
	Multiwavelet based multispectral image fusion for corona detection (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Wang X.; Yang H.-J.; Sui Y.-X.; Yan F.; Yan F. 收藏 \| 浏览/下载：29/0 \| 提交时间：2013/03/25 Image fusion refers to the integration of complementary information provided by various sensors such that the new images are more useful for human or machine perception. Multiwavelet transform has simultaneous orthogonality symmetry compact support and vanishing moment which are not possible with scalar wavelet transform. Multiwavelet analysis can offer more precise image analysis than wavelet multiresolution analysis. In this paper a new image fusion algorithm based on discrete multiwavelet transform (DMWT) to fuse the dual-spectral images generated from the corona detection system is presented. The dual-spectrum detection system is used to detect the corona and indicate its exact location. The system combines a solar-blind UV ICCD with a visible camera where the UV image is useful for detecting UV emission from corona and the visible image shows the position of the corona. The developed fusion algorithm is proposed considering the feature of the UV and visible images adequately. The source images are performed at the pixel level. First a decomposition step is taken with the DMWT. After the decomposition step a pyramid for each source image in each level can be obtained. Then an optimized coefficient fusion rule consisting of activity level measurement coefficient combining and consistency verification is used to acquire the fused coefficients. This process reduces the impulse noise of UV image. Finally a new fused image is obtained by reconstructing the fused coefficients using inverse DMWT. This image fusion algorithm has been applied to process the multispectral UV/visible images. Experimental results show that the proposed method outperforms the discrete wavelet transform based approach.
	Study of removing striping noise in CCD image (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Liu H.; Liu H.; Liu H. 收藏 \| 浏览/下载：16/0 \| 提交时间：2013/03/25 Striping noise is the common system noise during formation of image using linear array CCD and has the character of periodicity directivity and banding distributing. It can be caused by errors in internal calibration devices or by slight gain/offset differences among the elements that conform the array of detectors. Striping noise covers up useful information in CCD image and brings adverse effect to image interpretation. On the basis of analyzing wavelet decomposed coefficient the regularities of distribution about striping noise in wavelet coefficient is found thereby the method of wavelet threshold selection which is suitable to striping noise distribution is put forward. According to Donoho's method about denoising using wavelet the image including striping noise is processed. Comparing the power spectrum of processed image with the one of original image polluted by striping noise in frequency field we find pulse brought by striping noise is removed and the goal which reserves image details and reduces stripes is achieved.