Robustness in Statistical Pattern Recognition

This title is printed to order. This book may have been self-published. If so, we cannot guarantee the quality of the content. In the main most books will have gone through the editing process however some may not. We therefore suggest that you be aware of this before ordering this book. If in doubt check either the author or publisher’s details as we are unable to accept any returns unless they are faulty. Please contact us if you have any questions.

This monograph is devoted to problems of robust (stable) statistical pattern recognition. Experimental data to be classified usually deviate from assumed hypothetical probability models of the data. In such cases traditional decision rules constructed by means of the classical pattern recognition theory based on a fixed hypothetical model of the data often become non-stable, and the classification risk increases non-controllably. The book concentrates on three main problems: robustness evaluation for classical decision rules in the presence of distortion; estimation of critical levels of distortions for given values of the robustness factor; and the construction of robust decision rules with stable classification risk regarding certain types of distortions. Theoretical results are illustrated by computer modelling and by application to medical diagnostics. Audience: This volume is primarily intended for mathematicians, statisticians, and engineers in applied mathematics, computer science and cybernetics. It is also recommended as a textbook for a one-semester course for advanced undergraduate and graduate students training in the indicated fields.