该文将深度学习用于遥感图像融合,在训练深度网络时加入了结构风险最小化的损失函数,提出了一种基于深度支撑值学习网络的融合方法.为了避免图像融合过程中的信息损失,在传统卷积神经网络的基础上,取消了特征映射层的下采样过程,构建了...该文将深度学习用于遥感图像融合,在训练深度网络时加入了结构风险最小化的损失函数,提出了一种基于深度支撑值学习网络的融合方法.为了避免图像融合过程中的信息损失,在传统卷积神经网络的基础上,取消了特征映射层的下采样过程,构建了深度支撑值学习网络(Deep Support Value Learning Networks,DSVL Nets),DSVL Nets网络模型包含5个隐藏层,每一层的基本结构由卷积层和线性层构成,该基本单元提供了一种多尺度、多方向、各向异性、非下采样的冗余变换,该模型在网络训练完毕之后,取出各卷积层和第5个隐藏层的线性层作为网络模型的输出层.输出层的各卷积层图像融合采用绝对值取大法,得到融合后的各卷积层图像;另外,将线性层图像分别在过完备字典上进行稀疏表示,并对稀疏系数采用绝对值取大法进行融合,得到融合后的线性层图像;最后将融合后的各卷积层和线性层图像重构得到结果图像.文中使用QuickBird和Geoeye卫星数据验证本文所提方法的有效性,实验结果表明,与PCA、AWLP、PN-TSSC和SVT算法相比较,该文所提方法的融合结果无论在主观视觉还是客观评价指标上均优于对比算法,较好地保持了图像的光谱信息和空间信息.展开更多
Support vector machines （SVMs） have been introduced as effective methods for solving classification problems. However, due to some limitations in practical applications, their generalization performance is sometimes...Support vector machines （SVMs） have been introduced as effective methods for solving classification problems. However, due to some limitations in practical applications, their generalization performance is sometimes far from the expected level. Therefore, it is meaningful to study SVM ensemble learning. In this paper, a novel genetic algorithm based ensemble learning method, namely Direct Genetic Ensemble （DGE）, is proposed. DGE adopts the predictive accuracy of ensemble as the fitness function and searches a good ensemble from the ensemble space. In essence, DGE is also a selective ensemble learning method because the base classifiers of the ensemble are selected according to the solution of genetic algorithm. In comparison with other ensemble learning methods, DGE works on a higher level and is more direct. Different strategies of constructing diverse base classifiers can be utilized in DGE. Experimental results show that SVM ensembles constructed by DGE can achieve better performance than single SVMs, hagged and boosted SVM ensembles. In addition, some valuable conclusions are obtained.展开更多
Comparing with the traditional network education supporting system, this system introduced by the paper adds to many functions based on web 2.0 besides of traditional teaching functions, such as Blog, RSS, etc. These ...Comparing with the traditional network education supporting system, this system introduced by the paper adds to many functions based on web 2.0 besides of traditional teaching functions, such as Blog, RSS, etc. These functions accelerate that learner interactive with system. The practice proves that network education supporting system based on web 2.0 can improve learner＇s positivity of active studying and improves the network education＇s quality.展开更多
文摘该文将深度学习用于遥感图像融合,在训练深度网络时加入了结构风险最小化的损失函数,提出了一种基于深度支撑值学习网络的融合方法.为了避免图像融合过程中的信息损失,在传统卷积神经网络的基础上,取消了特征映射层的下采样过程,构建了深度支撑值学习网络(Deep Support Value Learning Networks,DSVL Nets),DSVL Nets网络模型包含5个隐藏层,每一层的基本结构由卷积层和线性层构成,该基本单元提供了一种多尺度、多方向、各向异性、非下采样的冗余变换,该模型在网络训练完毕之后,取出各卷积层和第5个隐藏层的线性层作为网络模型的输出层.输出层的各卷积层图像融合采用绝对值取大法,得到融合后的各卷积层图像;另外,将线性层图像分别在过完备字典上进行稀疏表示,并对稀疏系数采用绝对值取大法进行融合,得到融合后的线性层图像;最后将融合后的各卷积层和线性层图像重构得到结果图像.文中使用QuickBird和Geoeye卫星数据验证本文所提方法的有效性,实验结果表明,与PCA、AWLP、PN-TSSC和SVT算法相比较,该文所提方法的融合结果无论在主观视觉还是客观评价指标上均优于对比算法,较好地保持了图像的光谱信息和空间信息.
基金This work was supported by National Basic Research Programof China under Grant2002cb312200 01 3National Nature ScienceFoundation of China under Grant60174038.
文摘Support vector machines （SVMs） have been introduced as effective methods for solving classification problems. However, due to some limitations in practical applications, their generalization performance is sometimes far from the expected level. Therefore, it is meaningful to study SVM ensemble learning. In this paper, a novel genetic algorithm based ensemble learning method, namely Direct Genetic Ensemble （DGE）, is proposed. DGE adopts the predictive accuracy of ensemble as the fitness function and searches a good ensemble from the ensemble space. In essence, DGE is also a selective ensemble learning method because the base classifiers of the ensemble are selected according to the solution of genetic algorithm. In comparison with other ensemble learning methods, DGE works on a higher level and is more direct. Different strategies of constructing diverse base classifiers can be utilized in DGE. Experimental results show that SVM ensembles constructed by DGE can achieve better performance than single SVMs, hagged and boosted SVM ensembles. In addition, some valuable conclusions are obtained.
文摘Comparing with the traditional network education supporting system, this system introduced by the paper adds to many functions based on web 2.0 besides of traditional teaching functions, such as Blog, RSS, etc. These functions accelerate that learner interactive with system. The practice proves that network education supporting system based on web 2.0 can improve learner＇s positivity of active studying and improves the network education＇s quality.
