>> 自然科学版期刊 >> 2019年03期 >> 正文
特征加权的模糊C有序均值聚类算法
供稿: 刘永利;王恒达;刘静;杨立身 时间: 2019-04-16 次数:

作者:刘永利;王恒达;刘静;杨立身

作者单位:河南理工大学计算机科学与技术学院

摘要:Fuzzy C-ordered-means clustering(FCOM)算法基于排序进行模糊聚类,虽然其鲁棒性得到提高,但是耗时的排序操作降低了算法的效率。本文基于FCOM算法,将排序加权模式进行改进,提出一种特征加权的模糊C有序均值聚类算法(feature weighted fuzzy C-ordered-means clustering,FWFCOM)。为了验证算法的有效性,选取6个UCI数据集进行试验。结果表明,FWFCOM算法不仅在聚类准确率和鲁棒性方面有较好的表现,而且运行效率也得到有效提升。

基金:国家自然科学基金资助项目(61872126);河南省科技攻关计划项目(172102210279);河南省高等学校青年骨干教师专项项目(2015GGJS-068);河南省高校基本科研业务费专项项目(NSFRF1616);

关键词:模糊聚类;特征加权;排序;鲁棒性;

DOI:10.16186/j.cnki.1673-9787.2019.3.17

分类号:TP311.13;O223

Abstract:The fuzzy C-ordered-means clustering (FCOM) algorithm is based on a sorting operation. Although the robustness of this algorithm is improved, but the time-consuming sorting operation significantly reduces clustering efficiency. Based on the FCOM algorithm, the weighted sorting model was improved, and a feature weighted fuzzy C-ordered-means (FWFCOM) clustering algorithm was proposed. Six UCI data sets were selected for experiments to verify the effectiveness of the proposed algorithm. The results showed that the FWFCOM algorithm performed well in clustering accuracy and robustness, and the clustering efficiency was effectively improved.

最近更新