The Fuzzy CLustering and Data Analysis Toolbox is a collection of Matlab
functions. Its propose is to divide a given data set into subsets (called
clusters), hard and fuzzy partitioning mean, that these transitions between
the subsets are crisp or gradual.
CURE(CLustering Using Representatives)是一種針對(duì)大型數(shù)據(jù)庫(kù)的高效的聚類算法。基于劃分的傳統(tǒng)的聚類算法得到的是球狀的,相等大小的聚類,對(duì)異常數(shù)據(jù)比較脆弱。CURE采用了用多個(gè)點(diǎn)代表一個(gè)簇的方法,可以較好的處理以上問題。并且在處理大數(shù)據(jù)量的時(shí)候采用了隨機(jī)取樣,分區(qū)的方法,來提高其效率,使得其可以高效的處理大量數(shù)據(jù)。