检索结果-内蒙古大学图书馆

High-precision deformation monitoring algorithm for GBSAR system: rail determination phase error compensation

Science China(information Sciences) 2016年第8期59卷 204-219页

作者： Cheng HU Mao ZHU Tao ZENG Weiming TIAN Cong MAO Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

In recent years, the repeat-pass GBSAR(ground based synthetic aperture radar) system has demonstrated its capacity to acquire deformation. Nevertheless, in a variety of applications, it needs to measure the deformation with the precision up to 0.1 mm, which could not be reached by utilizing the traditional PS(permanent scatterer) algorithm in most cases. Generally, one of the main reasons could be summarized into the phase error caused by the rail determination error, because the precision of rail determination might degrade during long working hours. However, the traditional PS algorithm could not compensate for the phase error caused by the rail determination error. In order to solve the problems, we modify the conventional PS ***, we deduced the transformation relationship between the rail determination error and its corresponding interferometric phase error. Then, the phase errors caused by the atmosphere and the rail determination error were jointly compensated. The experimental data, which were obtained in Fangshan District in Beijing(China), were used to test and verify the performance of the new algorithm. After the comparison between the results processed by the new algorithm and those processed by the traditional algorithm, the proposed method demonstrated its ability to obtain high-precision deformation.

关键词： permanent scatterer(PS) synthetic aperture radar(SAR) ground-based SAR deformation monitoring radar

来源：评论

学校读者我要写书评

暂无评论

A beam search approach based on action space for the 2D rectangular packing problem 1

引用

9th International Symposium on Intelligence Computation and Applications, ISICA 2017

作者： Yin, Aihua Wang, Lei Hu, Dongping Rao, Hao Deng, Song School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics NanchangJiangxi330023 China College of Computer Science and Technology Wuhan University of Science and Technology WuhanHubei430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System WuhanHubei430081 China

ISBN: (数字)9789811316517

ISBN: (纸本)9789811316500

A beam search algorithm is presented to solve the 2D rectangular packing problem. The basic algorithms work according to 7 rule vectors of heuristic selection rules designed to select a corner-sticking action. Furthermore, the trade-off scheme of breadth first search (BFS) and the depth first search (DFS) increases the algorithm’s effectiveness and efficiency. The improved version of the algorithm adopts a rough phase to get a height for the stripe and a refine phase to obtain better solution for the problem. Computational experiments run on two sets of well-known benchmark instances and the computational results show that the algorithm outperforms the current best algorithms. Especially, for two benchmark instances ZDF6 and ZDF7, our algorithm finds the best packing configurations so far. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Suppressing the effects of ionospheric scintillation on geosynchronous SAR by optimised orbit design

Suppressing the effects of ionospheric scintillation on geos...

引用

2017 International Conference on Radar Systems, Radar 2017

作者： Li, YuanHao Liu, XiangRong Hu, Cheng Dong, XiChao School of Information and Electronics Beijing Institute of Technology 100081 China National Key Laboratory of Science and Technology on Test Physics and Numerical Mathematics 100076 China Beijing Key Laboratory of Embedded Real-time information Processing Technology 100081 China

ISBN: (纸本)9781785615153

An L band geosynchronous synthetic aperture radar (GEO SAR) will be sensitive to ionosphere scintillation because of its low carrier frequency. Meanwhile, because of the high orbit, GEO SAR has a higher probability to meet ionospheric scintillation. In this paper, we propose an orbit strategy for eliminating the impacts of ionospheric scintillation. It is realized by selecting a proper orbit element (time past perigee) to avoid imaging for the sensitive region of ionospheric scintillation during the eruption time interval of ionospheric scintillation with the highest probability. Finally, the simulation based on systems tool kit (STK) software was conducted to verify the effectiveness of the method. © 2017 Institution of Engineering and technology. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Robust and fast iterative sparse recovery method for space-time adaptive processing

引用

Science China(information Sciences) 2016年第6期59卷 199-211页

作者： Xiaopeng YANG Yuze SUN Tao ZENG Teng LONG Beijing Key Laboratory of Embedded Real-time Information Processing Technology School of Information and Electronics Beijing Institute of Technology

Conventional space-time adaptive processing(STAP) requires large numbers of independent and identically distributed(i.i.d) training samples to ensure the performance of clutter suppression, which is hard to be achieved in practical complex nonhomogeneous environment. In order to improve the performance of clutter suppression with small training sample support, a robust and fast iterative sparse recovery method for STAP is proposed in this paper. In the proposed method, the sparse recovery of clutter spatial-temporal spectrum and the calibration of space-time overcomplete dictionary are achieved iteratively. Firstly, the robust solution of sparse recovery is derived by regularized processing, which can be calculated recursively based on the block Hermitian matrix property, afterwards the mismatch of space-time overcomplete dictionary is calibrated by minimizing the cost function. The proposed method can not only alleviate the effect of noise and dictionary mismatch, but also reduce the computational cost caused by direct matrix inversion. Finally, the proposed method is verified based on the simulated and the actual airborne phased array radar data, which shows that the proposed method is suitable for practical complex nonhomogeneous environment and provides better performance compared with conventional STAP methods.

关键词： space-time adaptive processing(STAP) sparse recovery robust iteration computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Feature Matching Method For Simultaneous Localization And Mapping 2

A Feature Matching Method For Simultaneous Localization And ...

引用

2017 IEEE 2nd information technology, Networking, Electronic and Automation Control Conference (ITNEC 2017)

作者： Chen Xiangkui Jiang Min Zuo Liangyu Jiang jian College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System

ISBN: (纸本)9781509064151;9781509064144

Simultaneous Localization and Mapping is an important technology which help a mobile robot to determine its location and build the environment map. Recently, the RGBD sensor is widely used in the robot, research on RGBD-SLAM becomes a hot topic. In order to calculate the movement parameters of robot, feature matching is adopted to register the two adjacent RGBD images in the video stream. This paper proposed an improved feature matching method for RGBDSLAM. The experiment results show that, compared with the traditional SIFT feature matching methods for RGBD-SLAM,the performance of the proposed method is improved significantly.

关键词： Simultaneous Localization and Mapping Feature Matching SIFT FREAK

来源：评论

学校读者我要写书评

暂无评论

An improved Chinese text multi-label classification method based on CNN

引用

Journal of Physics: Conference Series 2020年第1期1619卷

作者： Yuanxia Xin Zhi Zhang Collage of Computer Science and Technology Wuhan University of Science and Technology Wuhan 430065 Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan 430065 Hubei China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan 430065 Hubei China

Text multi-label classification technology can accurately and quickly classify text information into related categories or topics, and help people quickly locate the required content in massive information resources, which is of great significance in application. As the traditional classification algorithm is faced with the problems of low classification accuracy due to the low correlation of data labels, unbalanced label data and few short text feature words, this paper firstly performs hierarchical pre-processing on label data to transform multi-label classification into hierarchical text multi-classification. At the same time, an improved multi-label classification algorithm Multi-label Convolutional Neural Networks (ML-CNN) is proposed. Based on the TensorFlow framework, a CNN model is designed and different training models are constructed for each level of label classification. According to the number of classification levels, the output of the upper level label is stitched to the original input tail as the next level of input. Experiments on the description information of 500,000 Chinese products with labels, show that the improved algorithm will significantly improve the classification accuracy and the accuracy of each level can reach more than 88%, which proves the feasibility and effectiveness of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Analysis and Planning Analysis Management System Based on Tensorflow Machine Learning Algorithms

引用

Journal of Physics: Conference Series 2019年第1期1325卷

作者： Shuang Hu Li Huang Feng Bai Jun Zhang School of Computer Science and Technology Wuhan University of Science and Technology Intelligent Information Processing and Real-time Industrial System Hubei Key Laboratory Institute

At present, machine learning is quite popular, and tensorflow framework is also very popular. This system takes the plan management system as the practice platform, realizes the data analysis function through the machine learning understanding and the key point. Most of the current market are planning management system, but there is no self-analysis ability, need to base on data, there are limitations. Firstly, the system collects training data such as weight, body fat rate and so on, then builds a deep learning neural network, and finally runs the model to realize plan analysis, so as to help users analyze the feasibility of the plan and provide suggestions for users, and the analysis results will be displayed through processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multiscale Superpixel-Level Salient Object Detection Model Using Local-Global Contrast Cue

引用

Journal of Shanghai Jiaotong university(Science) 2017年第1期22卷 121-128页

作者：穆楠徐新王英林张晓龙 School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology School of Information Management and Engineering Shanghai University of Finance and Economics

The goal of salient object detection is to estimate the regions which are most likely to attract human's visual attention. As an important image preprocessing procedure to reduce the computational complexity, salient object detection is still a challenging problem in computer vision. In this paper, we proposed a salient object detection model by integrating local and global superpixel contrast at multiple scales. Three features are computed to estimate the saliency of superpixel. Two optimization measures are utilized to refine the resulting saliency map. Extensive experiments with the state-of-the-art saliency models on four public datasets demonstrate the effectiveness of the proposed model.

关键词： salient object detection superpixel multiple scales local contrast global contrast TP 391.4 A

来源：评论

学校读者我要写书评

暂无评论

Optimal protein structure extraction with clustering algorithm

Optimal protein structure extraction with clustering algorit...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Jiafu Zhao Xiaolong Zhang Min Cao Hubei Hubei Key Laboratory of Intelligent Information Wuhan University of Science and Technology Wuhan China Key Laboratory of Intelligent Information Processing and Real-time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China. 430065

In this paper, we use K-means++ and AP algorithm to cluster the five protein similarity measures of RMSD, TM, MaxSub, GDT-TS and GDT-HA. As for the selection of the number of clusters, using the measures of Scikit-learn to value the cluster result to attain an optimal number of clusters. Also, we optimize the AP algorithm through the change of the preference value, whose value changes from the general mean value, max value, min value to mean value of 4 neighbour at the corresponding position. Moreover, we propose a cluster center selection algorithm based on mean distance from data points to cluster center and number of data points in a cluster, which could automatically delete exception value, thus improve the accuracy of selection cluster center. After the cluster and selection of cluster center, we get better similarity between protein structure and natural protein compare to the earlier results, which means a lot to the protein structure prediction.

关键词： Proteins Clustering algorithms Predictive models Amino acids Indexes Prediction algorithms Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Scene Classification via Multi-feature Fusion

Remote Sensing Image Scene Classification via Multi-feature ...

引用

第30届中国控制与决策会议

作者： Ruiyao Liu Xiaoyong Bian Yuxia Sheng School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System School of Information Science and Engineenring Wuhan University of Science and Technology

In this papers, classification of remote sensing image scene is investigated. A scene classification approach based on multi-feature fusion has been proposed. In the proposed approach, three types of features are extracted. Specifically, extended multi-attribute profile(EMAP)-based texture feature, saliency-based shape feature and color ones. The texture features are extracted by EMAP. Furthermore, the Hu invariant moments are extracted from the saliency map, where the saliency map is obtained by frequency-tuned saliency detection. Meanwhile, the color moments are extracted as the color features from the image scenes. As for EMAP-based features, dimension reduction via principal component analysis(PCA) is first performed and combined with other two types of features to form a compact feature representation. Finally, support vector machine(SVM) is employed to classify the remote sensing image scenes. The experiments on the two challenging image scene datasets are performed to show that the proposed method is simple, yet efficient to implement, comparing with the state-of-the-arts.

关键词： Scene classification morphological attribute profile saliency map feature extraction

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：