コードベクトルの分離・結合を考慮した自己組織化マップに基づくクラスタリング手法

抄録

A method is proposed for clustering data that results in more accurate clustering when clusters are close to each other. The method takes into account the continuity of the data by using a self-organizing map showing the separation and combination of code vectors. Using this map reduces the dependence of fitting of code vectors. The proposed method can be thus used to obtain accurate clustering.