ID 原文 译文
843 针对分布复杂且离群类型多样的数据集进行离群检测困难的问题，提出基于相对距离的反 k 近邻树离群检测方法 RKNMOD(Reversed K-Nearest Neighborhood)。 For outlier detection difficulty of data sets with complex distribution and various types of outliers, a newoutlier detection method based on reversed k-nearest neighborhood MST of relative distance measure is proposed.
844 首先，将经典欧氏距离、对象局部密度和对象邻域结合，定义了对象的相对距离，能同时有效检出全局和局部离群点。 Firstly, rel-ative distance of object is defined with the combination of classical distance, local density and neighborhood of object, whichcan be used to detect global outliers and local outliers both.
845 其次，以最小生成树结构为基础，采取最大边切割法以快速分割离群点和离群簇。 Secondly, on basis of minimum spanning tree structure, by tactics of maximum-edge-cutting, outliers and outlier clusters can be obtained.
846 最后，人工合成数据集和 UCI 数据集试验均表明，新算法的检测准确率更高，为分布异常且离群类型多样的数据集的离群检测提供了一条有效的新途径。 Finally, experiments of synthetic and UCI data setsshow that the new algorithm is much more correct and effective. It is a new effective way for detecting outliers of data sets with abnormal distribution and diversity outlier types.
847 基于邻域广义模糊聚类算法能够分割含噪声灰度图像，但是如果图像灰度分布不均衡或者起始的聚类中心设置不合适仍会导致该算法分割失败， The spatial generalized fuzzy c-means clustering algorithm (GFCM _S)is a popular technique for image segmentation, but it is not so effective when the image has the features of unequal cluster sizes or the initial cluster centerswe choose are improper.
848 为此，提出一种基于混沌优化和改进模糊聚类算法相融合的图像分割算法。 In this paper, for solving the above shortcomings of GFCM_S, a novel algorithm incorporating cha-os optimization and improved fuzzy c-means (CIGFCM_S)is proposed.
849 首先，将每一类的隶属度之和引入基于邻域广义模糊聚类算法的目标函数中，从而能够均衡较大类和较小类对目标函数的贡献。 Firstly, each size of clusters is integrated into the objective function of GFCM_S so as to equalize the contribution of larger and smaller clusters to the objective function.
850 其次，以新目标函数为基础，利用拉格朗日乘子法推导出相应的隶属度和聚类中心。 Sec-ondly, the iteratively membership degree and cluster centers are deduced by the Lagrange multiplier method.
851 再次，将混沌优化和改进模糊聚类算法联合得到最优解，即最合适的聚类中心， Thirdly, a new iterative strategy is used to seek the optimal solutions.
852 细节上，每一代的聚类中心分别由混沌系统和改进模糊聚类算法两种路径产生，具有较小目标函数的聚类中心进入下一个迭代进程。 In detail, the optimal solutions of next generation are searched by two-paths, one path originates chaos optimization and the other is obtained by updating membership degree and cluster centers on the basis of current optimal solutions, and then the better solutions go to next generation until the end.