针对低信噪比条件下微多普勒调制易被噪声污染的问题,提出了一种基于复数域概率主成分分析(Complex Probabilistic Principal Component Analysis,CPPCA)模型的噪声稳健分类算法来实现低分辨雷达体制下三类飞机目标(喷气式飞机、螺旋桨...针对低信噪比条件下微多普勒调制易被噪声污染的问题,提出了一种基于复数域概率主成分分析(Complex Probabilistic Principal Component Analysis,CPPCA)模型的噪声稳健分类算法来实现低分辨雷达体制下三类飞机目标(喷气式飞机、螺旋桨飞机和直升机)的分类.算法依据三类飞机多普勒谱调制的差异,提出两维反映这种差异的微动特征.为了提高微动特征在低信噪比条件下的分类性能,利用CPPCA模型对雷达复回波信号建模并结合Akaike信息量准则(Akaike’s Information Criterion,AIC)来自适应地确定回波中主成分的个数从而实现对数据的噪声抑制.基于实测数据的实验结果表明,该算法在较低信噪比条件下能够获得较好的噪声抑制和分类性能.展开更多
Traditionally, airborne time-domain electromagnetic (ATEM) data are inverted to derive the earth model by iteration. However, the data are often highly correlated among channels and consequently cause ill-posed and ...Traditionally, airborne time-domain electromagnetic (ATEM) data are inverted to derive the earth model by iteration. However, the data are often highly correlated among channels and consequently cause ill-posed and over-determined problems in the inversion. The correlation complicates the mapping relation between the ATEM data and the earth parameters and thus increases the inversion complexity. To obviate this, we adopt principal component analysis to transform ATEM data into orthogonal principal components (PCs) to reduce the correlations and the data dimensionality and simultaneously suppress the unrelated noise. In this paper, we use an artificial neural network (ANN) to approach the PCs mapping relation with the earth model parameters, avoiding the calculation of Jacobian derivatives. The PC-based ANN algorithm is applied to synthetic data for layered models compared with data-based ANN for airborne time-domain electromagnetic inversion. The results demonstrate the PC-based ANN advantages of simpler network structure, less training steps, and better inversion results over data-based ANN, especially for contaminated data. Furthermore, the PC-based ANN algorithm effectiveness is examined by the inversion of the pseudo 2D model and comparison with data-based ANN and Zhody's methods. The results indicate that PC-based ANN inversion can achieve a better agreement with the true model and also proved that PC-based ANN is feasible to invert large ATEM datasets.展开更多
[Objective] The aim was to research development plan of major agriculture-oriented county (MAOA or MAOC hereafter) based on territorial function. [Method] The relationship between Major Function Oriented Zoning (MF...[Objective] The aim was to research development plan of major agriculture-oriented county (MAOA or MAOC hereafter) based on territorial function. [Method] The relationship between Major Function Oriented Zoning (MFOZ hereafter) and agricultural development is explored with the case of Long'an County in Guangxi. [Result] In the research, agricultural function, featured by composition and diversification, is considered one of territorial function typs, contributed by ecology, land, industries and population. With Long'an as a study case, it can be concluded that the plan of major agriculture-oriented counties is as follows: With guidance of territorial function, the counties should formulate the strategies of major function oriented zones, strive for more social and economic resources for agricultural development, extend agricultural functions, enhance the role of agricultural additional functions, strengthen ecological conservation, improve agricultural productivity and transportation, reinforce exchange of countryside with other regions. In addition, attention should be paid to reconstruction of population and industry pattern for redistribution on the basis of evaluation on bearing capacity of resources and environment. [Conclusion] In future, major agriculture oriented county should coordinate relationship among agriculture, industries, ecology and population with rational distribution of territorial function in county to guarantee stable and sustainable agricultural development.展开更多
The Neighborhood Preserving Embedding(NPE) algorithm is recently proposed as a new dimensionality reduction method.However, it is confined to linear transforms in the data space.For this, based on the NPE algorithm, a...The Neighborhood Preserving Embedding(NPE) algorithm is recently proposed as a new dimensionality reduction method.However, it is confined to linear transforms in the data space.For this, based on the NPE algorithm, a new nonlinear dimensionality reduction method is proposed, which can preserve the local structures of the data in the feature space.First, combined with the Mercer kernel, the solution to the weight matrix in the feature space is gotten and then the corresponding eigenvalue problem of the Kernel NPE(KNPE) method is deduced.Finally, the KNPE algorithm is resolved through a transformed optimization problem and QR decomposition.The experimental results on three real-world data sets show that the new method is better than NPE, Kernel PCA(KPCA) and Kernel LDA(KLDA) in performance.展开更多
In multiagent reinforcement learning, with different assumptions of the opponents’ policies, an agent adopts quite different learning rules, and gets different learning performances. We prove that, in multiagent doma...In multiagent reinforcement learning, with different assumptions of the opponents’ policies, an agent adopts quite different learning rules, and gets different learning performances. We prove that, in multiagent domains, convergence of the Q values is guaranteed only when an agent behaves optimally and its opponents’ strategies satisfy certain conditions, and an agent can get best learning performances when it adopts the same learning algorithm as that of its opponents.展开更多
In China,the economic systems of many small-scale resource-based regions are confronted with realizing sustainable development through economic transformation. This paper,taking 37 coal-resource-based counties in Chin...In China,the economic systems of many small-scale resource-based regions are confronted with realizing sustainable development through economic transformation. This paper,taking 37 coal-resource-based counties in China as objects,evaluates the economic transformation capacities of the counties by principal component analysis (PCA). Based on the comprehensive principal component values of >1,0–1 and <0,the economic transformation capacities of the counties are classified into strong,common and weak grades. Then,the paper proposes the developmental countermeasures according to different transformation capacities. For the counties with strong transformation capacities,it is crucial to make scientific positioning and rationally exploite resources in view of the developing characteristics and modes of those counties; as for the counties with common transformation capacities,the preparation and perfection of basic transformation conditions are still important aspects; as for the counties with weak transformation capacities,shifting from ″passive transfromation″ to ″active transformation″ in light of resources conditions is necessary.展开更多
文摘针对低信噪比条件下微多普勒调制易被噪声污染的问题,提出了一种基于复数域概率主成分分析(Complex Probabilistic Principal Component Analysis,CPPCA)模型的噪声稳健分类算法来实现低分辨雷达体制下三类飞机目标(喷气式飞机、螺旋桨飞机和直升机)的分类.算法依据三类飞机多普勒谱调制的差异,提出两维反映这种差异的微动特征.为了提高微动特征在低信噪比条件下的分类性能,利用CPPCA模型对雷达复回波信号建模并结合Akaike信息量准则(Akaike’s Information Criterion,AIC)来自适应地确定回波中主成分的个数从而实现对数据的噪声抑制.基于实测数据的实验结果表明,该算法在较低信噪比条件下能够获得较好的噪声抑制和分类性能.
基金supported by the National Natural Science Foundation of China (Grant No. 40974039)High-Tech Research and Development Program of China (Grant No.2006AA06205)Leading Strategic Project of Science and Technology, Chinese Academy of Sciences (XDA08020500)
文摘Traditionally, airborne time-domain electromagnetic (ATEM) data are inverted to derive the earth model by iteration. However, the data are often highly correlated among channels and consequently cause ill-posed and over-determined problems in the inversion. The correlation complicates the mapping relation between the ATEM data and the earth parameters and thus increases the inversion complexity. To obviate this, we adopt principal component analysis to transform ATEM data into orthogonal principal components (PCs) to reduce the correlations and the data dimensionality and simultaneously suppress the unrelated noise. In this paper, we use an artificial neural network (ANN) to approach the PCs mapping relation with the earth model parameters, avoiding the calculation of Jacobian derivatives. The PC-based ANN algorithm is applied to synthetic data for layered models compared with data-based ANN for airborne time-domain electromagnetic inversion. The results demonstrate the PC-based ANN advantages of simpler network structure, less training steps, and better inversion results over data-based ANN, especially for contaminated data. Furthermore, the PC-based ANN algorithm effectiveness is examined by the inversion of the pseudo 2D model and comparison with data-based ANN and Zhody's methods. The results indicate that PC-based ANN inversion can achieve a better agreement with the true model and also proved that PC-based ANN is feasible to invert large ATEM datasets.
基金Supported by Key Program of National Natural Science Foundation of China(40830741)~~
文摘[Objective] The aim was to research development plan of major agriculture-oriented county (MAOA or MAOC hereafter) based on territorial function. [Method] The relationship between Major Function Oriented Zoning (MFOZ hereafter) and agricultural development is explored with the case of Long'an County in Guangxi. [Result] In the research, agricultural function, featured by composition and diversification, is considered one of territorial function typs, contributed by ecology, land, industries and population. With Long'an as a study case, it can be concluded that the plan of major agriculture-oriented counties is as follows: With guidance of territorial function, the counties should formulate the strategies of major function oriented zones, strive for more social and economic resources for agricultural development, extend agricultural functions, enhance the role of agricultural additional functions, strengthen ecological conservation, improve agricultural productivity and transportation, reinforce exchange of countryside with other regions. In addition, attention should be paid to reconstruction of population and industry pattern for redistribution on the basis of evaluation on bearing capacity of resources and environment. [Conclusion] In future, major agriculture oriented county should coordinate relationship among agriculture, industries, ecology and population with rational distribution of territorial function in county to guarantee stable and sustainable agricultural development.
文摘The Neighborhood Preserving Embedding(NPE) algorithm is recently proposed as a new dimensionality reduction method.However, it is confined to linear transforms in the data space.For this, based on the NPE algorithm, a new nonlinear dimensionality reduction method is proposed, which can preserve the local structures of the data in the feature space.First, combined with the Mercer kernel, the solution to the weight matrix in the feature space is gotten and then the corresponding eigenvalue problem of the Kernel NPE(KNPE) method is deduced.Finally, the KNPE algorithm is resolved through a transformed optimization problem and QR decomposition.The experimental results on three real-world data sets show that the new method is better than NPE, Kernel PCA(KPCA) and Kernel LDA(KLDA) in performance.
文摘In multiagent reinforcement learning, with different assumptions of the opponents’ policies, an agent adopts quite different learning rules, and gets different learning performances. We prove that, in multiagent domains, convergence of the Q values is guaranteed only when an agent behaves optimally and its opponents’ strategies satisfy certain conditions, and an agent can get best learning performances when it adopts the same learning algorithm as that of its opponents.
基金Under the auspices of Key Program of National Natural Science Foundation of China (No. 40635030)
文摘In China,the economic systems of many small-scale resource-based regions are confronted with realizing sustainable development through economic transformation. This paper,taking 37 coal-resource-based counties in China as objects,evaluates the economic transformation capacities of the counties by principal component analysis (PCA). Based on the comprehensive principal component values of >1,0–1 and <0,the economic transformation capacities of the counties are classified into strong,common and weak grades. Then,the paper proposes the developmental countermeasures according to different transformation capacities. For the counties with strong transformation capacities,it is crucial to make scientific positioning and rationally exploite resources in view of the developing characteristics and modes of those counties; as for the counties with common transformation capacities,the preparation and perfection of basic transformation conditions are still important aspects; as for the counties with weak transformation capacities,shifting from ″passive transfromation″ to ″active transformation″ in light of resources conditions is necessary.