Random Subspace Based Local Mean Classifier for Cancer Classification

Abstract

A new classifier for cancer classification named Random Subspace Local Mean Classifier (RSLMC) is presented in this paper. The method firstly divides the feature space into several subspaces, secondly in each subspace classifies the test samples according to the distances of each sample with the local mean vectors of each class, finally combines the subspace classification results of each test sample into a final result. The experiment results on cancer datasets suggest that the proposed classifier often gives better performance than other comparing method.

Related Papers

• → Local Subspace Classifier(1997)34 cited
• → Robust Multidimensional Matched Subspace Classifiers Based on Weighted Least-Squares(2007)14 cited
• → Research on Financial Risk Prediction Based on Improved Random Subspace(2022)1 cited
• → A semi-random subspace method for classification ensembles(2013)1 cited
• Subspace ensembles for face recognition(2010)