Robust EM Clustering via Mixture Model for Multivariate Regression
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
We propose a robust clustering method based on a mixture of multivariate regression models. The proposed REM algorithm is based on the EM algorithm applied to a Huberized multivariate normal density designed to downweight the effect of outliers. We discuss practical issues of the REM algorithms, and assess the performance of the proposed clustering method through Monte Carlo simulations. We also demonstrate how REM works in clustering the gene expression data of Saccharomyces Cerevisiae with the corresponding motif scores as covariates.
Abstract
We propose a robust clustering method based on a mixture of multivariate regression models. The proposed REM algorithm is based on the EM algorithm applied to a Huberized multivariate normal density designed to downweight the effect of outliers. We discuss practical issues of the REM algorithms, and assess the performance of the proposed clustering method through Monte Carlo simulations. We also demonstrate how REM works in clustering the gene expression data of Saccharomyces Cerevisiae with the corresponding motif scores as covariates.
참고문헌 (22)
- Fraley C, "How many clusters? which clustering method? answers via model-based cluster analysis", Comput J, 41, pp.578~588 (1998)
- Dempster AP, "Maximum likelihood estimation from incomplete data via the em algorithm", J Roy Stat Soc, 39, pp.1~38 (1977)
- Yuille AL, "Statistical physics, mixtures of distributions and the emalgorithm", Neural Comput, 6, pp.334~340 (1994)
- Xu L, "On convergence properties of the EM algorithm for gaussian mixtures", Neural Comput, 8, pp.129~151 (1996)
- Scaling em clustering to large databases, "Bradley P", Microsoft Research, ~ (1999)
- Roweis S, "A unifying review of linear gaussian models", Neural Comput, 11, pp.305~345 (1999)
- Ordonez C, "Sqlem: Fast clustering in sql using the em algorithm", Proc Acm Sigmod Conf, pp.559~570 (2000)
- McLachlan GJ, "Finite mixture models" (2000), John Wiley and Sons
- Rocke DM, "Identification of outliers in multivariate data", J Am Stat Assoc, 91, pp.1047~1061 (1996)
- Mclachlan GJ, "Mixture models: inference and applications to clustering" (1988), Marcel Dekker, Inc
- Campbell NA, "Mixture models and atypical values", Math Geol, 16, pp.465~477 (1984)
- McLachlan GJ, "Lecture Notes in Computer Science", pp.658~666 (1998), Springer-Verlag
- Luan Y, "Clustering the time-course gene expression data using a mixed-effects model with b-splines", Bioinformatics, 19, pp.474~482 (2003)
- Wang L, "Group scad regression analysis for microarray time course gene expresion data", Bioinformatics, 23, pp.1486~1494 (2007)
- Hubert L, "Comparing partitions", J Classif, 2, pp.193~218 (1985)
- Rand WM, "Objective criteria for the evaluation of clustering methods", J Am Stat Assoc, 66, pp.846~850 (1971)
- An empirical study on principal component analysis for clustering gene expression data, "Yeung KY", Department of Computer Science and Engineering, University of Washington, ~ (2000)
- Azzalini A, "Distributions generated by perturbation of symmetry with emphasis on a multivariate skew t-distribution", J Roy Stat Soc B Met, 65, pp.367~389 (2003)
- Wang L, "Variable selection in nonparametric varying-coefficient models for analysis of repeated measurements", J Am Stat Assoc, 103, pp.1556~1569 (2008)
- Spellman PT, "Comprehensive identification of cell cycleregulated genes of the yeast saccharomyces cerevisiae by microarray hybridization", Mol Biol Cell, 9, pp.3273~3297 (1998)
- Tibshirani R, "Regression shrinkage and selection via the lasso", J Roy Stat Soc B Met, 58, pp.267~288 (1996)
- Efron B, "Least angle regression", Ann Stat, 32, pp.407~499 (2004)