ID 原文 译文
893 目前已经提出的增量式属性约简算法仅适用于符号型的信息系统， The incremental attribute reduction algorithm already proposed is only applicable to symbolic information systems.
894 而很少有对混合信息系统进行相关的研究，这促使在混合信息系统下构建相关的增量式属性约简算法。 However, there are few related studies on mixed information systems, which promotes the construction of the related incremental attribute reduction algo-rithm under the mixed information system.
895 区分度是用于设计属性约简的一种重要方法， The discernibility degree is an important method used for designing attribute re-duction.
896 本文将传统的区分度在混合信息系统下进行推广，提出邻域区分度的概念， In this paper, the traditional discernibility degree is generalized under the mixed information system, and the concept of neighborhood discernibility degree is presented.
897 然后分别研究了邻域区分度在混合信息系统下对象增加和对象减少时的增量式学习， Then, the incremental learning of neighborhood discernibility degree isstudied respectively when objects increase or objects decrease under the mixed information system.
898 最后根据这种增量式学习分别提出了对应的增量式属性约简算法。 Finally, according to this incremental learning, the corresponding incremental attribute reduction algorithms are proposed, respectively.
899 UCI 数据集上的相关实验结果表明，所提出的增量式属性约简比非增量式属性约简能够更快速的更新约简结果。基于深度学习的高光谱遥感图像地物分类是目前研究的热点。 The related ex-perimental results on the UCI data set show that the proposed incremental attribute reduction can update the reduction resultsmore quickly than the non incremental attribute reduction.
900 但由于其参数规模大以及结构复杂，深度网络通常需要大量训练样本和较长训练时间，如何在小规模样本下建立深度学习监督分类模型是需要解决的关键问题。 Due to the massive parameters and complex structure, deep learning networks are usually trained in a longtime with large-scale training samples.
901 本文提出了一种小规模样本下高光谱图像分类的空-谱卷积稠密网络算法，称为 SSCDenseNet，其包含三种新颖的架构策略: In this paper, we propose a spatial-spectral convolutional dense network (SSC-DenseNet)which mainly targets limited samples for hyperspectral image classification. Three novel strategies are proposed to construct the proposed network.
902 (1)空-谱分离卷积，即采取光谱维一维卷积和空间维二维卷积的分离卷积结构构成隐层单元，并通过多个隐层单元堆叠构造深度网络; First, a spatial-spectral separable convolution method is adopted to make up a hidden layer unit with a spectral one-dimensional convolutional layer and a spatial two-dimensional convolutional layer;then the deep net-work is constructed by stacking multiple units.