A novel clustering algorithm based on the deviation factor model

IF 1.4 Q4 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

International Journal of Computational Science and Engineering Pub Date : 2019-01-01 DOI:10.1504/IJCSE.2019.10022775

Chen Jungan, Chen Jinyin, Yang Dongyong

引用次数: 4

Abstract

For classical clustering algorithms, it is difficult to find clusters that have non-spherical shapes or varied size and density. In view of this, many methods have been proposed in recent years to overcome this problem, such as introducing more representative points per cluster, considering both interconnectivity and closeness, and adopting the density-based method. However, the density defined in DBSCAN is decided by minPts and Eps, and it is not the best solution to describe the data distribution of one cluster. In this paper, a deviation factor model is proposed to describe the data distribution and a novel clustering algorithm based on artificial immune system is presented. The experimental results show that the proposed algorithm is more effective than DBSCAN, k-means, etc.

查看原文本刊更多论文

一种基于偏差因子模型的聚类算法

对于传统的聚类算法，很难找到具有非球形或大小和密度变化的聚类。鉴于此，近年来提出了许多方法来克服这一问题，例如在每个聚类中引入更多的代表性点，同时考虑互联性和紧密性，以及采用基于密度的方法。然而，DBSCAN中定义的密度是由minpt和Eps决定的，它不是描述一个集群的数据分布的最佳解决方案。本文提出了一种描述数据分布的偏差因子模型，并提出了一种基于人工免疫系统的聚类算法。实验结果表明，该算法比DBSCAN、k-means等算法更有效。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Computational Science and Engineering COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS-

CiteScore

4.00

自引率

40.00%

发文量

期刊介绍： Computational science and engineering is an emerging and promising discipline in shaping future research and development activities in both academia and industry, in fields ranging from engineering, science, finance, and economics, to arts and humanities. New challenges arise in the modelling of complex systems, sophisticated algorithms, advanced scientific and engineering computing and associated (multidisciplinary) problem-solving environments. Because the solution of large and complex problems must cope with tight timing schedules, powerful algorithms and computational techniques, are inevitable. IJCSE addresses the state of the art of all aspects of computational science and engineering with emphasis on computational methods and techniques for science and engineering applications.