[1]YANG Xiao-bing,HE Ling-min,KONG Fan-sheng.A noise-resistant clustering algorithm for switching regression models[J].CAAI Transactions on Intelligent Systems,2009,4(6):497-501.[doi:10.3969/j.issn.1673-4785.2009.06.005]
Copy

A noise-resistant clustering algorithm for switching regression models

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 4 Number of periods: 2009 6 Page number: 497-501 Column: 学术论文—机器学习 Public date: 2009-12-25
Title:
A noise-resistant clustering algorithm for switching regression models
Author(s):
YANG Xiao-bing1;  HE Ling-min1;  KONG Fan-sheng2
1. Department of Computer Science， China Jiliang University, Hangzhou 310018, China; 2. College of Computer Science, Zhejiang University, Hangzhou 310012, China
Keywords:
switching regression models;  clustering;  noise-resistant clustering algorithm
CLC:
TP301.6
DOI:
10.3969/j.issn.1673-4785.2009.06.005
Abstract:
Clustering methods for switching regression models usually neglect the effects of noise. As a result, errors usually exist if clustering is carried out in a noisy environment. In order to overcome the effects of noise, a new clustering algorithm, a noiseresistant clustering algorithm, was proposed. The algorithm partitions the dataset into two subdatasets, a noiseless dataset and a noisy dataset, and then performs clustering analysis on the noiseless dataset to estimate parameters. By continuous simultaneous adjustment of the noisy and noiseless datasets and by continuously revising estimated parameters, the results of clustering were improved. Simulation experiments demonstrated that the algorithm efficiently clusters noisy datasets and can provide good estimates of parameters.
References:
［1］HAN Jiawei，KAMBER M. 数据挖掘概念与技术［M］. 范明, 孟小峰，译. 北京:机械工业出版社, 2001: 223-261.
［2］HAMERMESH D S. Wage bargains, threshold effects, and the Phillips curve［J］. Quarterly Journal of Economics, 1970, 84(3):501-517.
［3］QUANDT R E. A new approach to estimating switching regressions［J］. J Amer Statist Ass, 1972, 67(338): 306-310.
［4］QUANDT R E, RAMSEY J B. Estimating mixtures of normal distributions and switching regressions［J］. J Amer Statist Ass, 1978, 73: 730-752.
［5］HOSMER D W. Maximum likelihood estimates of the parameters of a mixture of two regression lines［J］. Communications in Statistics, 1974, 3(10):995-1005.
［6］BEZDEK J C. Pattern recognition with fuzzy objective function algorithms［M］. New York: Plenum Press, 1981:88-94.
［7］HATHAWAY R J, BEZDEK J C. Switching regression models and fuzzy clustering［J］. IEEE Trans on Fuzzy Systems, 1993, 1(3):195-204.
［8］OHTA T, YAMAKAWA A, ICHIHASHI H, et al. Projection pursuit switching regression［C］//Proc of 5th International Conference on Soft Computing. Iizuka, Japan, 1998：775-778.
［9］OHTA T, YAMAKAWA A, ICHIHASHI H，et al. Projection pursuit switching regression for analysis of psychological feelings［J］. Journal of Biomedical Soft Computing and Human Sciences, 1998, 4(1): 15-21.
［10］沈红斌, 王士同, 吴小俊. 离群模糊核聚类算法［J］. 软件学报, 2004, 15(7)：1021-1029. 
?SHEN Hongbin, WANG Shitong, WU Xiaojun. Fuzzy kernel clustering with outliers［J］.Journal of Software, 2004, 15(7): 1021-1029.
［11］WANG Shitong, JIANG Haifeng, LU Hongjun. A new integrated clustering algorithm GFC and switching regression［J］. International Journal of Pattern Recognition and Artificial Intelligence, 2002, 16(4):433-446.
［12］陆宏钧, 江海峰, 王士同. 关于切换回归的集成模糊聚类算法GFC［J］. 软件学报，2002，13(10)：1905-1914. 
LU Hongjun, JIANG Haifeng,WANG Shitong. An integrated fuzzy clustering algorithm GFC for switching regressions［J］. Journal of Software, 2002, 13(10): 1905-1914.
Similar References:

Memo

-

Last Update: 2010-02-17

Copyright © CAAI Transactions on Intelligent Systems