基于特征选择的洪水聚类分析

Flood Clustering Analysis Based On Feature Selection

采用Mitra算法对洪水进行了特征选择,并利用Kmeans和FCM聚类方法对某流域47场洪水进行了聚类分析。结果表明:Mitra算法可有效去除指标提取时的冗余特征,Kmeans与FCM聚类结果吻合较好,各类洪水特点鲜明。

Mitra algorithm was employed to select features of flood samples, and Kmeans and FCM were employed as the methods of 47 floods clustering in a basin. The results indicate that Mitra algorithm is effective in reducing redundant features. The results of flood clustering by Kmeans and FCM respectively have good agreement and the features of each flood category is obvious.