论文信息 - Robust classification of high-dimensional data

Robust classification of high-dimensional data

COMPSTAT 2004 section: Classification. Abstract: In this paper we introduce a robust method to classify high- dimensional observations. We consider the SIMCA (Soft Independent Mod- elling of Class Analogies) approach to obtain a classification rule. Although a primary goal of this method was to detect outlying observations, the method itself is not robust. Therefore we will consider a robust classification method that shares the same ideas as the SIMCA approach. This robust method is based on a robust method for principal component analysis for high- dimensional data.

Mia Hubert | Karlien Vanden Branden

[1] M. Hubert,et al. A fast method for robust principal components with applications to chemometrics , 2002 .

[2] M. Hubert,et al. Robust methods for partial least squares regression , 2003 .

[3] Svante Wold,et al. Pattern recognition by means of disjoint principal components models , 1976, Pattern Recognit..

[4] Christopher J. Merz,et al. UCI Repository of Machine Learning Databases , 1996 .

[5] Catherine Blake,et al. UCI Repository of machine learning databases , 1998 .

[6] Mia Hubert,et al. Fast cross-validation in robust PCA , 2004 .

[7] Mia Hubert,et al. ROBPCA: A New Approach to Robust Principal Component Analysis , 2005, Technometrics.

[8] Randall D. Tobias,et al. Chemometrics: A Practical Guide , 1998, Technometrics.

[9] P. Rousseeuw. Multivariate estimation with high breakdown point , 1985 .