基于边缘峰度度量的特征缩减模糊聚类算法

对含有不重要特征、冗余特征的数据进行聚类,采用特征缩减模糊聚类(feature reduction fuzzy c-means,FRFCM)算法是有效的.该算法使用特征的均值方差比(mean-to-variance ratio,MVR)度量特征的重要性,删除权重小于阈值的特征,仅保留重要特征进行聚类,以提升算法的性能和...

Feature-reduction fuzzy clustering algorithm based on marginal kurtosis measure

The feature reduction fuzzy c-means(FRFCM) algorithm has been proven effective for clustering data with redundant features. The FRFCM can automatically compute individual feature weight, and simultaneously reduce these redundant feature component. However, it still has the following disadvantages: 1) the large MVR value of original features may become small if the data is normalized, and vice versa. 2) the MVR value of important features of some datasets is not necessarily large. 3) feature assignment is sensitive to initialization. The FRFCM may produce wrong weights if initialization is improper, which can deteriorate the clustering accurancy. Therefore, we first devise a new index, named marginal kurtosis measure(MKM), to measure the importance of features instead of using MVR index. Then, a novel and robust feature reduction fuzzy c-means clustering algorithm based marginal kurtosis measure is proposed. Experiments on synthetic and real-world dataset demonstrate that the proposed method is effective and efficient.