一种基于静电场概念的聚类算法  

A Novel Clustering Algorithm Based on Electrostatic Field Concepts

作　　者：李小喜[1] 辛永平[1] 陈疆萍[1] 张明学[2] 

机构地区：[1]空军工程大学导弹学院,陕西三原713800 [2]空军工程大学理学院,陕西西安710051

出　　处：《空军工程大学学报（自然科学版）》2010年第5期44-47,52,共5页Journal of Air Force Engineering University(Natural Science Edition)

基　　金：国防重点实验室基金资助项目(9140C8301011001)

摘　　要：在静电场中质心位于静电平衡或那些能够被接受的平衡位置处,基于这一思想提出了一种发现簇中心的新方法。根据静电场中电荷间的引力作用来确定质心位置,然后根据相应的准则(如最小距离准则等)使用选定的质心对数据点进行聚类。最后将提出的方法与K-means算法进行实验对比,结果表明该方法克服了K-means算法存在的问题,例如,对噪声和初始聚类中心敏感以及易于陷入局部最优等。该方法具有很高的效率,并且对多维数据集有强的鲁棒性。In this paper, a new method is presented for finding data clusters centroids. This method is proposed based on the concept of electrostatic field in which the eentroids are positioned at locations where an electrostatic equilibrium or balance can be achieved. After determining the centroids locations, criteria such as the minimum distance to centroid can be used for clustering data points. The performance of the proposed method is compared with that of the k - means algorithm through simulation experiments. The experimental results show that the proposed algorithm does not suffer from the problems associated with k - means, such as sensitivity to noise and initial selection of eentroids, and tendency to converge to poor local optimum.

关 键 词：静电场 静电平衡 K—means算法 簇中心 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]