跳到主要导航 跳到搜索 跳到主要内容

A New Method of Selecting K-means Initial Cluster Centers Based on Hotspot Analysis

  • Qu Chen
  • , Hong Yi
  • , Yujie Hu
  • , Xianrui Xu
  • , Xiang Li*
  • *此作品的通讯作者
  • East China Normal University
  • University of South Florida

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

The initial cluster centers of traditional K-means algorithm are randomly selected from spatially distributed data samples. This procedure may significantly affect the final clustering outputs and is unable to ensure a high-quality solution. This paper attempts to improve the quality of solution and the efficiency of clustering through selecting initial cluster centers based on hotspot analysis. An algorithm is developed to identify K hotspots as initial cluster centers. The proposed algorithm is compared to three existing methods in our experiments. Our results demonstrate that our method can generate similar but more stable clustering results with less number of iterations than others.

源语言英语
主期刊名Proceedings - 2018 26th International Conference on Geoinformatics, Geoinformatics 2018
编辑Shixiong Hu, Xinyue Ye, Kun Yang, Hongchao Fan
出版商IEEE Computer Society
ISBN(电子版)9781538676196
DOI
出版状态已出版 - 3 12月 2018
活动26th International Conference on Geoinformatics, Geoinformatics 2018 - Kunming, 中国
期限: 28 6月 201830 6月 2018

出版系列

姓名International Conference on Geoinformatics
2018-June
ISSN(印刷版)2161-024X
ISSN(电子版)2161-0258

会议

会议26th International Conference on Geoinformatics, Geoinformatics 2018
国家/地区中国
Kunming
时期28/06/1830/06/18

学术指纹

探究 'A New Method of Selecting K-means Initial Cluster Centers Based on Hotspot Analysis' 的科研主题。它们共同构成独一无二的学术指纹。

引用此