聚类分析
轮廓
k均值聚类
计算机科学
模式识别(心理学)
数据挖掘
数学
星团(航天器)
人工智能
统计
程序设计语言
出处
期刊:Advanced Materials Research
日期:2014-05-01
卷期号:951: 227-230
被引量:98
标识
DOI:10.4028/www.scientific.net/amr.951.227
摘要
Clustering is an important technology that can divide data patterns into meaningful groups, but the number of groups is difficult to be determined. This paper proposes an automatic approach, which can determine the number of groups using silhouette coefficient and the sum of the squared error.The experiment conducted shows that the proposed approach can generally find the optimum number of clusters, and can cluster the data patterns effectively.
科研通智能强力驱动
Strongly Powered by AbleSci AI