检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Muchen Dai Xiangguang Leng Boli Xiong Kefeng Ji State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System College of Electronic Science and Engineering National University of Defense Technology Changsha China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Water segmentation is a fundamental step for the information processing of SAR image, which plays an important role in ship detection, disaster monitoring and other applications. Because of the complexity of scenario in the SAR images, water segmentation of SAR image is a challenging task. Fewer convolutional neural networks (CNNs) have been developed for SAR image water segmentation in recent years, the accuracy and speed of CNN for water segmentation can be further improved. In this paper, we established a SAR water segmentation dataset based on the GF3 satellite data. then an improved water segmentation network based on Bilateral Segmentation Network (BiSeNet) is proposed. Further we propose a loss function based on edge area and a novel training data generation method to improve the segmentation ability of the network. Experimental results based on water segmentation dataset show that the proposed segmentation method has better segmentation accuracy and speed.

关键词： Image segmentation Radar polarimetry Image edge detection Training data Training Synthetic aperture radar Marine vehicles

来源：评论

学校读者我要写书评

暂无评论

A multi-layer network topology visualization layout based on Louvain community detection 3

A multi-layer network topology visualization layout based on...

引用

3rd IEEE International Conference on Data science in Cyberspace, DSC 2018

作者： Zhang, Xitao Wu, Lingda Yao, Zhonghua Yu, Shaobo Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781538642108

Community is one of the most important structure features of complex networks. It has important research significance for topological structure analysis, behavior prediction, cascading failure, percolation and spreading of multi-layer networks. Aiming at the problem that the existing multi-layer network visualization can't clearly show the community structure, a multi-layer network topology visualization layout based on Louvain community detection is proposed. Firstly, a complex network community discovery algorithm (Louvain) is used to perform the multi-layer network nodes at each layer and the community affiliation of the nodes is obtained at each layer;then, based on the traditional force-directed layout, the community force is added to the internal nodes of the community, so that all the nodes that belong to the same community are gathered to the community center, so as to achieve the effect of displaying the network community structure. The simulation results show that the algorithm has the characteristics of faster convergence and clearer community structure than the traditional visual layout algorithm. © 2018 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Reasearch on dynamic evolution model visualization of satellite communication network based on complex network 3

Reasearch on dynamic evolution model visualization of satell...

引用

3rd IEEE International Conference on Data science in Cyberspace, DSC 2018

作者： Liu, Chengxiang Xiong, Wei Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781538642108

In order to explore the dynamic evolution of satellite communication network, this paper carried out a visualization study on the dynamic evolution model of satellite communication network based on complex network theory. By constructing reasonable visual mission view and status view, the paper analyzes the properties of satellite communication network and also uses complex network theory to improve the modeling. Through the rule design and algorithm derivation of dynamic evolution model, it analyzes the detailed steps of the dynamic evolution of satellite communication network. By the experiments, it is proved that the dynamic evolution visualization model of satellite communication network conforms to the power law distribution of complex network, which lays a solid foundation for the follow-up study of satellite communication network. © 2018 IEEE.

关键词： complex networks

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural networks based for high spectral dimensional data classification 3

Convolutional neural networks based for high spectral dimens...

引用

3rd IEEE International Conference on Data science in Cyberspace, DSC 2018

作者： Zhu, Jiang Wu, Lingda Lu, Yi Jiao, Jiao Song, Xiaorui Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781538642108

Recent research has shown that deep learning is widely used to classify the high spectral dimensional data. Under limited samples, a novel method of high spectral dimensional data classification based on convolutional neural networks (CNNs) is proposed. By standardization and adding virtual samples, the sensitivity of models on the classification of objects and quantity of classification objects is reduced. The computational complexity and computation time are reduced by optimizing the gradient descent method and the learning rate calculation method. By setting up a suitable network structure, the generalization is improved. The experimental results show that compared with the traditional classification methods such as k-Nearest Neighbor (KNN), Logistic Regression (LR) and Support Vector Machine of Radial Basis Function Kernel (RBF-SVM), the method using convolutional neural network has more competitive results in computational efficiency and classification accuracy. © 2018 IEEE.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of moving ship target signal integration and detection in geosynchronous synthetic aperture radar

Performance analysis of moving ship target signal integratio...

引用

IET International Radar Conference 2018, IRC 2018

作者： Zhang, Ying Dong, Xichao Xiong, Wei Hu, Cheng Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing101416 China Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Ministry of Education Beijing100081 China

Geosynchronous synthetic aperture radar (GEO SAR) has the characteristics of wide coverage and short revisit time, which makes GEO SAR moving target indication more valuable than other platforms. This article analyses the influence of moving target on 'Stop-and-Go' error in GEO SAR, and then the accurate slant range model of moving target is constructed. The signal-to-noise ratio of the raw data echoes for moving ship target is very low because of the high satellite orbit altitude, so it cannot be detected by constant false alarm detection. Based on the accurate slant range model of moving target in GEO SAR, three kinds of integration methods are reconstructed, including moving target detection, Radon transform and generalised Radon Fourier transform (GRFT). The performance of these methods is compared through numerical simulation. GRFT can provide the best detection performance in a reasonable integration time. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Model-free Based Reinforcement Learning Control Strategy of Aircraft Attitude systems

Model-free Based Reinforcement Learning Control Strategy of ...

引用

Chinese Automation Congress (CAC)

作者： Dingcui Huang Jiangping Hu Zhinan Peng Bo Chen Mingrui Hao Bijoy Kumar Ghosh School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Texas Tech University Lubbock USA

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Traditional aircraft control algorithms have a strong dependence on system models, and are difficult to cope with the increasingly complex battlefield environment for intelligent aircrafts. In this paper, a model-free reinforcement learning is proposed to solve an attitude stabilization problem of an aircraft based online intelligent control strategy. The attitude control problem is firstly formulated as an optimal control problem, and then an adaptive dynamic programming (ADP) technology is applied to compute the corresponding nonlinear Hamilton-Jacobi-Bellman (HJB) equation. Then, an actor-critic neural network structure is established to learn the optimal controller online not requiring the information of the aircraft dynamics. The proposed intelligent control strategy enables the aircraft to adjust its attitude according to the actual mission targets and environments under the proposed online control strategy, so that autonomous learning and intelligent operation can be realized. Finally, simulation examples are presented to validate the proposed model-free based control strategy.

关键词： Atmospheric modeling Aircraft Adaptation models Mathematical model Aerodynamics Attitude control Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Denoising of hyperspectral images based on principal component analysis and adaptive sparse coding 10

Denoising of hyperspectral images based on principal compone...

引用

10th IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2018

作者： Xiaorui, Song Lingda, Wu Space Engineering University Science and Technology on Complex Electronic System Simulation Laboratory Beijing101416 China

ISBN: (纸本)9781538684795

In view of the special properties of hyperspectral images(HSI) in the transform domain, in this paper, a new denoising method of HSI based on principal component analysis(PCA) and adaptive sparse coding is proposed. Firstly, the principal component image of each channel is obtained by performing PCA transform on the noisy HSI. Then, the first PCA output channels which contain a majority of the total energy of an HSI data cube are retained, and the rest PCA output channels which contain a small amount of energy, termed noise component images, are subjected to noise reduction through an adaptive sparse coding method. The encoding dictionaries are learned from each channel of noise component images by an approach of online dictionary learning. Finally, the denoised HSI is obtained by the inverse PCA transform. The proposed method takes the advantages of PCA and adaptive sparse representation that has better adaptability to the HSI. It not only performs better in denoising, but also preserves the details and alleviates the blocking artifacts well. The effectiveness of the proposed approach to hyperspectral denoising, termed PCASpC, is illustrated in a series of experiments with synthetic and realworld data where it outperforms the state-of-the-art. © 2018 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Wireless sensor network localization approach based on bayesian MDS 5th

Wireless sensor network localization approach based on bayes...

引用

5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017

作者： Pei, Zhongmin Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing101416 China

ISBN: (纸本)9789811308956

The aim of wireless sensor networks (WSNs) are to perceive, collect and process the information of sensor nodes within the coverage of the network. As a bridge between the physical world and the digital one, WSNs have widely been applied in many fields. One of the key issues for most applications is to know the location of sensor nodes. Though localization algorithms based on multidimensional scaling (MDS), which only need several anchor nodes, have been proven to be robust with respect to range-based implementations, these methods are sensitive inaccuracy range measure. This article proposes a novel localization algorithm based on Bayesian MDS, named as MDS-MAP(P, B), where P and B denote the use of patching of local maps and Bayesian MDS, respectively. Experimental results in real-world systems show that our method is more robust and efficient. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Visualization of pairwise data: An overview 3

Visualization of pairwise data: An overview

引用

3rd IEEE International Conference on Data science in Cyberspace, DSC 2018

作者： Pei, Zhong-Min Xiong, Ming-Hui Xiong, Wei Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing101416 China

ISBN: (纸本)9781538642108

It is difficult for some applications to extract feature functions in the process of data visualization. Focus on the problem of large-scale pairwise data visualization, the paper first introduces and analysis the problem. Then the current mainstream methods for pairwise data visualization are analyzed. On the basis of active learning and configuration suture, the paper proposes a fast visualization method. The overall research framework, the key technologies are presented to provide some research ideas and recommendations for pairwise data visualization. © 2018 IEEE.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Method for constructing multi-dimensional feature map of malicious code

引用

Journal of Physics: Conference Series 2021年第4期1748卷

作者： Haocong Ma Ji Zhang Junhua Zhou Xiang Zhai Junjie Xue Hang Ji State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing 100854 China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing simulation Center Beijing 100854 China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854 China School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China

Malicious code is characterized by a large number of types, rapid increase in number, continuous update of transmission routes, and continuous enhancement of back analysis and back detection methods. Therefore, how to effectively detect and analyze malicious code has been a problem of great concern. This paper studies the features of binary file and disassembly file of malicious code, introduces the concept of information gain, and proposes a method to construct the multi-dimensional characteristic graph of malicious code. Finally, the convolutional neural network is used to classify the multi-dimensional feature graph of malicious code, which provides a new idea for the feature extraction of malicious code.

关键词：

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：