ID 原文 译文
49667 为考察其适应性，一组实际数据用来说明各种参数估计方法的使用情况，同时，分别用指数分布和威布尔分布拟合该组数据，并计算相应的统计量。 To inspect its adaptability, a group of actual data used to illustrate the usage of various parameter estimation methods, at the same time, respectively, with the exponential distribution and weibull distribution fitting the group data, and calculate the corresponding statistics.
49668 结果表明，根据3种分布的极大似然估计量和K-S值，Lindley分布对该组数据具有最好的适应性。 Results show that according to the three kinds of distribution of the maximum likelihood estimator and K - S value, Lindley distribution data has better adaptability to the group.
49669 为了充分利用稀疏表示分类信息和高光谱图像的空间信息，提出结合马尔可夫随机场的加权条件稀疏表示高光谱图像分类算法。 In order to make full use of sparse representation classification information and spatial information of hyperspectral image, put forward in combination with markov random field weighted conditional sparse representation of hyperspectral image classification algorithm.
49670 该算法对稀疏表示分解后的残差向量建立条件稀疏表示模型，在计算残差向量的类别归属时引入频段方差信息; The algorithm of sparse representation condition for establishing the residual vector of the decomposed sparse representation model, when calculating the residual vector of and introduced frequency variance information;
49671 利用光谱信息散度从信息熵的角度挖掘重构光谱中的类别鉴定信息; Using spectral information divergence from the Angle of information entropy, mining categories in refactoring spectrum identification information;
49672 在期望最大化算法模型中，将条件稀疏模型与光谱信息散度模型相结合，使算法具备迭代自更新的能力; In the expectation maximization algorithm model, the condition of sparse model combined with spectral information divergence model, since the update algorithm with iterative ability;
49673 将马尔可夫随机场引入加权条件稀疏表示算法，在算法时间复杂度不变的情况下，对高光谱图像的空间信息予以提取。 Markov random field to sparse representation algorithm weighted conditions, on the basis of the algorithm time complexity, the spatial information of hyperspectral image extraction.
49674 仿真结果表明，该算法能够有效地提高分类精度，且在不同试验数据下具备良好的稳定性。 The simulation results show that the algorithm can effectively improve the classification accuracy, and good stability under different test data.
49675 提取稳定有效的目标特征对于低分辨雷达的目标识别分类有着重要意义。 Stable and effective target feature extracting for low resolution radar target recognition classification has important significance.
49676 在提取目标基本特征雷达散射截面积(radar cross section，RCS)与频谱熵值的基础上，提出了一种基于特征概率分布曲线的目标分类方法。 Basic features in the extraction of target radar scattering cross section area (radar cross section, the RCS) and spectral entropy, on the basis of this paper proposes a classification method based on the characteristics of probability distribution curve of the target.