Clustering of relational data containing noise and outliers
Clustering of relational data containing noise and outliers
复制标题
DOI：
10.1109/fuzzy.1998.686326
复制
发表时间：
1998-05
期刊：
影响因子：
--
通讯作者：
S. Sen;R. Davé
中科院分区：
文献类型：
--
作者：
S. Sen;R. Davé
将噪声聚类算法的概念应用到几种模糊关系数据聚类算法中，使其对噪声和离群点具有更强的鲁棒性。所考虑的方法包括Roubens（1978）、海瑟薇等人（1994）和FANNY（考夫曼和Rouseeuw（1990））提出的技术。通过对FANNY算法的推广，提出了一种新的模糊关系数据聚类算法。FRC算法具有相同的目标函数的关系模糊c-均值算法。然而，通过使用基于拉格朗日乘子技术的直接目标函数最小化，推导出最小化的必要条件，而不施加关系数据是从距对象数据的欧几里得距离度量导出的限制。通过几个例子证明了新算法的鲁棒性。
The concept of noise clustering algorithm is applied to several fuzzy relational data clustering algorithms to make them more robust against noise and outliers. The methods considered include techniques proposed by Roubens (1978), Hathaway et al. (1994) and FANNY by Kaufman and Rouseeuw (1990). A new fuzzy relational data clustering (FRC) algorithm is proposed through generalization of FANNY. The FRC algorithm is shown to have the same objective functional as the relational fuzzy c-means algorithm. However, through use of direct objective function minimization based on the Lagrangian multiplier technique, the necessary conditions for minimization are derived without imposition of the restriction that the relational data is derived from Euclidean measure of distance from object data. Robustness of the new algorithm is demonstrated through several examples.