クラスタリング分析におけるSOM 法と K-means 法の性質の比較

抄録

Clustering is a method of grouping data based on the similarity between them, and is widely used in marketing, image recognition, medical data, and other fields. The K-means method is a representative calculation method for unsupervised non-hierarchical clustering. In this study, we compared the Self-Organizing Maps, which is also a non-hierarchical clustering method, with the K-means method.