Linear dimension reduction in classification: adaptive procedure for optimum results

Authors:
Karsten Luebke;Claus Weihs
Affiliations:
Hochschule für Oekonomie und Management, Dortmund, Germany 44139;Department of Statistics, Dortmund University of Technology, Dortmund, Germany 44221
Venue:
Advances in Data Analysis and Classification
Year:
2011

Citing 6
Cited 0

Numerical recipes in C (2nd ed.): the art of scientific computing

Numerical recipes in C (2nd ed.): the art of scientific computing
Machine learning, neural and statistical classification

Machine learning, neural and statistical classification
Ranking Learning Algorithms: Using IBL and Meta-Learning on Accuracy and Time Results

Machine Learning
Facts, Conjectures, and Improvements for Simulated Annealing

Facts, Conjectures, and Improvements for Simulated Annealing
Applied Adaptive Statistical Methods: Tests of Significance and Confidence Intervals (Asa-Siam Series on Statistics and Applied Probability)

Applied Adaptive Statistical Methods: Tests of Significance and Confidence Intervals (Asa-Siam Series on Statistics and Applied Probability)
Rapid and brief communication: Improving feature extraction by replacing the Fisher criterion by an upper error bound

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Linear dimension reduction plays an important role in classification problems. A variety of techniques have been developed for linear dimension reduction to be applied prior to classification. However, there is no single definitive method that works best under all circumstances. Rather a best method depends on various data characteristics. We develop a two-step adaptive procedure in which a best dimension reduction method is first selected based on the various data characteristics, which is then applied to the data at hand. It is shown using both simulated and real life data that such a procedure can significantly reduce the misclassification rate.