How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classif...How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.展开更多
A new iterative greedy algorithm based on the backtracking technique was proposed for distributed compressed sensing(DCS) problem. The algorithm applies two mechanisms for precise recovery soft thresholding and cuttin...A new iterative greedy algorithm based on the backtracking technique was proposed for distributed compressed sensing(DCS) problem. The algorithm applies two mechanisms for precise recovery soft thresholding and cutting. It can reconstruct several compressed signals simultaneously even without any prior information of the sparsity, which makes it a potential candidate for many practical applications, but the numbers of non-zero(significant) coefficients of signals are not available. Numerical experiments are conducted to demonstrate the validity and high performance of the proposed algorithm, as compared to other existing strong DCS algorithms.展开更多
remote sensing of woody vegetation in savannas has been inhibited by its complex stand structure and abundant vegetation species.An understanding of the distribution and spatial variation in savanna vegetation is crit...remote sensing of woody vegetation in savannas has been inhibited by its complex stand structure and abundant vegetation species.An understanding of the distribution and spatial variation in savanna vegetation is critical for making timely assessments of the ecosystem conditions.This study investigated the possibility of improving the prediction of woody vegetation in tropical savannas using an approach that integrates spatial statistics and remote sensing.展开更多
Many studies have been done in cognitive radios to maximize the network efficiency. There is always a trade-off between sensing and transmission time which has been addressed fully in the literature. There is also som...Many studies have been done in cognitive radios to maximize the network efficiency. There is always a trade-off between sensing and transmission time which has been addressed fully in the literature. There is also some missed idle times during the waiting phase when secondary user finds the channel busy. Therefore, the longer the transmission time is, the higher the successfully delivered bits would be and the higher the missed idle times in the waiting stage would be expected. In this work, we formulate these missed idle times to addressed this trade-off. Furthermore, interference due to PU re-occupancy is modelled in successful transmitted time and in collision probability. Moreover, we derive secondary user's packet delay distribution using phase type model at which retransmission due to collision results from both sensing error and PU re-occupancy is considered. Thanks to derived delay distribution, any statistical moments of delay could be found as a closed form mathematical expression. These moments can be used as constraints for applications with delay sensitive packets. Numerical results are given to clarify the network metrics. Finally, the optimized values for sensing and transmission time are computed using genetic algorithm in order to maximize access efficiency.展开更多
For ship targets with complex motion,it is difficult for the traditional monostatic inverse synthetic aperture radar(ISAR)imaging to improve the cross-range resolution by increasing of accumulation time.In this paper,...For ship targets with complex motion,it is difficult for the traditional monostatic inverse synthetic aperture radar(ISAR)imaging to improve the cross-range resolution by increasing of accumulation time.In this paper,a distributed ISAR imaging algorithm is proposed to improve the cross-range resolution for the ship target.Multiple stations are used to observe the target in a short time,thereby the effect of incoherence caused by the complex motion of the ship can be reduced.The signal model of ship target with three-dimensional(3-D)rotation is constructed firstly.Then detailed analysis about the improvement of crossrange resolution is presented.Afterward,we propose the methods of parameters estimation to solve the problem of the overlap or gap,which will cause a loss of resolution and is necessary for subsequent processing.Besides,the compressed sensing(CS)method is applied to reconstruct the echoes with gaps.Finally,numerical simulations are presented to verify the effectiveness and the robustness of the proposed algorithm.展开更多
单主用户信号的出现主要引起多天线接收信号取样协方差矩阵中极值特征值的变化,而多主用户信号的出现则会同时扰动取样协方差矩阵极值特征值和其他特征值,此时,经典的极值特征值检测算法则会表现出次佳的检测性能。针对这一问题,本研究...单主用户信号的出现主要引起多天线接收信号取样协方差矩阵中极值特征值的变化,而多主用户信号的出现则会同时扰动取样协方差矩阵极值特征值和其他特征值,此时,经典的极值特征值检测算法则会表现出次佳的检测性能。针对这一问题,本研究设计了一种基于极值特征值差与特征值几何平均(difference of extreme eigenvalues and geometric average of eigenvalues,DEEGAE)的多主用户信号检测判决规则;提出了一种基于Wishart矩阵特征值统计分布理论的感知判决门限的闭式求解方法。该算法在频谱感知过程中直接利用认知用户的多天线接收数据构造判决规则并实施感知判决,具有全盲检测的优点;通过融合2种极限特征值门限分析结果,提高了非渐近感知条件下感知结果的准确性。Monte-Carlo仿真试验表明,新算法具有比经典的最大最小特征值之比算法和协方差绝对值检测算法更优的多主用户信号检测性能,同时能获得比传统基于最大最小特征值之差及其改进算法更为可靠的检测结果;与此同时,新算法的检测性能随着样本数目以及天线数目的增大而显著提升。展开更多
基金supported by the National Natural Science Foundation of China(U1435220)
文摘How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.
基金Supported by National Natural Science Foundation of China（61170147） Major Cooperation Project of Production and College in Fujian Province（2012H61010016） Natural Science Foundation of Fujian Province（2013J01234）
基金Projects(61203287,61302138,11126274)supported by the National Natural Science Foundation of ChinaProject(2013CFB414)supported by Natural Science Foundation of Hubei Province,ChinaProject(CUGL130247)supported by the Special Fund for Basic Scientific Research of Central Colleges of China University of Geosciences
文摘A new iterative greedy algorithm based on the backtracking technique was proposed for distributed compressed sensing(DCS) problem. The algorithm applies two mechanisms for precise recovery soft thresholding and cutting. It can reconstruct several compressed signals simultaneously even without any prior information of the sparsity, which makes it a potential candidate for many practical applications, but the numbers of non-zero(significant) coefficients of signals are not available. Numerical experiments are conducted to demonstrate the validity and high performance of the proposed algorithm, as compared to other existing strong DCS algorithms.
文摘remote sensing of woody vegetation in savannas has been inhibited by its complex stand structure and abundant vegetation species.An understanding of the distribution and spatial variation in savanna vegetation is critical for making timely assessments of the ecosystem conditions.This study investigated the possibility of improving the prediction of woody vegetation in tropical savannas using an approach that integrates spatial statistics and remote sensing.
基金supported by Islamic Azad University,Boroujerd Branch,Iran
文摘Many studies have been done in cognitive radios to maximize the network efficiency. There is always a trade-off between sensing and transmission time which has been addressed fully in the literature. There is also some missed idle times during the waiting phase when secondary user finds the channel busy. Therefore, the longer the transmission time is, the higher the successfully delivered bits would be and the higher the missed idle times in the waiting stage would be expected. In this work, we formulate these missed idle times to addressed this trade-off. Furthermore, interference due to PU re-occupancy is modelled in successful transmitted time and in collision probability. Moreover, we derive secondary user's packet delay distribution using phase type model at which retransmission due to collision results from both sensing error and PU re-occupancy is considered. Thanks to derived delay distribution, any statistical moments of delay could be found as a closed form mathematical expression. These moments can be used as constraints for applications with delay sensitive packets. Numerical results are given to clarify the network metrics. Finally, the optimized values for sensing and transmission time are computed using genetic algorithm in order to maximize access efficiency.
基金supported by the National Natural Science Foundation of China(61871146)the Fundamental Research Funds for the Central Universities(FRFCU5710093720)。
文摘For ship targets with complex motion,it is difficult for the traditional monostatic inverse synthetic aperture radar(ISAR)imaging to improve the cross-range resolution by increasing of accumulation time.In this paper,a distributed ISAR imaging algorithm is proposed to improve the cross-range resolution for the ship target.Multiple stations are used to observe the target in a short time,thereby the effect of incoherence caused by the complex motion of the ship can be reduced.The signal model of ship target with three-dimensional(3-D)rotation is constructed firstly.Then detailed analysis about the improvement of crossrange resolution is presented.Afterward,we propose the methods of parameters estimation to solve the problem of the overlap or gap,which will cause a loss of resolution and is necessary for subsequent processing.Besides,the compressed sensing(CS)method is applied to reconstruct the echoes with gaps.Finally,numerical simulations are presented to verify the effectiveness and the robustness of the proposed algorithm.
文摘单主用户信号的出现主要引起多天线接收信号取样协方差矩阵中极值特征值的变化,而多主用户信号的出现则会同时扰动取样协方差矩阵极值特征值和其他特征值,此时,经典的极值特征值检测算法则会表现出次佳的检测性能。针对这一问题,本研究设计了一种基于极值特征值差与特征值几何平均(difference of extreme eigenvalues and geometric average of eigenvalues,DEEGAE)的多主用户信号检测判决规则;提出了一种基于Wishart矩阵特征值统计分布理论的感知判决门限的闭式求解方法。该算法在频谱感知过程中直接利用认知用户的多天线接收数据构造判决规则并实施感知判决,具有全盲检测的优点;通过融合2种极限特征值门限分析结果,提高了非渐近感知条件下感知结果的准确性。Monte-Carlo仿真试验表明,新算法具有比经典的最大最小特征值之比算法和协方差绝对值检测算法更优的多主用户信号检测性能,同时能获得比传统基于最大最小特征值之差及其改进算法更为可靠的检测结果;与此同时,新算法的检测性能随着样本数目以及天线数目的增大而显著提升。
