一种基于扰动分析的三支谱聚类算法
A Three-Way Spectral Clustering Algorithm Based on Perturbation Analysis
摘要:
本文在多路谱聚类算法(NJW算法)的基础上进行三支聚类算法构造。主要思想是针对每个对象进行加权运算，利用多路谱聚类算法的稳定性，重复进行聚类运算从而获得加权结果。根据其加权后对全体对象的扰动影响，将其划入核心域或边界域。对S_Dbw(c)指标进行改造使其可以表示核心域与边界域的离散程度。最后分别在人工与UCI数据集上对算法进行测试，有较好效果。
Abstract:
We structure a three-way Clustering Algorithm Based on NJW Algorithm. The main idea is that each object, making weighted arithmetic, repeats clustering arithmetic to obtain the weighted results, which benefits from the stability of NJW Algorithm. According to the perturbation for all objects, we can classify the object into core or fringe regions. The compact degree of core and fringe regions can be described by the modified S_Dbw(c) index. Testing the algorithm on the artificial and UCI data sets, the results meet expectation.
参考文献
|
[1]
|
Jain, A.K., Murty, M.N. and Flynn, P.J. (1999) Data Clustering: A Review. ACM Computing Survey, 31, 264-323.
https://doi.org/10.1145/331499.331504
|
|
[2]
|
Anderberg, M.R. (1973) Cluster Analysis for Application. Academic Press, New York.
|
|
[3]
|
Omran, M.G.H., Engelbrecht, A.P. and Salman, A. (2007) An Overview of Clustering Methods. Intelligent Data Analysis, 11, 583-605.
|
|
[4]
|
Xu, R. and Wunsch, D. (2005) Survey of Clustering Algorithms. IEEE Transactions on Neural Networks, 16, 645- 678.
https://doi.org/10.1109/TNN.2005.845141
|
|
[5]
|
孙吉贵, 刘杰, 赵连宇. 聚类算法研究[J]. 软件学报, 2008, 19(1): 48-61.
|
|
[6]
|
Halkidi, M. and Vazirgiannis, M. (2002) Clustering Validity Assessment: Finding the Optimal Partitioning of a Data Set. Proceedings IEEE International Conference on Data Mining, 29 November-2 December 2001.
http://ieeexplore.ieee.org/abstract/document/989517/
|