Can I read A parallel network of modified 1-NN and k-NN classifiers – Application to remote-sensing image classification on EtoBox?

A parallel network of modified 1-NN and k-NN classifiers – Application to remote-sensing image classification by Adam Jóźwik; Sebastiano Serpico; Fabio Roli is a Computer Science article available to read on EtoBox.

What is A parallel network of modified 1-NN and k-NN classifiers – Application to remote-sensing image classification about?

A parallel network of modified 1-NN classifiers and k-NN classifiers is described and compared with a standard k-NN classifier. All the component classifiers decide between two classes only. The number of all possible pairs of classes determines the number of the component classifiers. The global decision is formed by voting of all the component classifiers. Each of the component classifiers operates as follows. For each class i a certain area A is constructed in such a i way that area A covers all training samples from the class i and possibly a small number of training samples from other i classes. In the classification phase, if a sample lies outside of all areas A , then the classification is refused. When it belongs i only to one of the areas A , then the classification is performed by the 1-NN rule. Samples that lie in an overlapping area of i Ž . some A are classified by the k-NN rule. Such a classification rule, in this paper called a combined 1-NN, k-NN rule, is i used by all component classifiers. Two feature selection sessions are recommended for each of the component classifiers: one to minimize the size of the overlapping areas and another to minimize the error rate fo

Who reads A parallel network of modified 1-NN and k-NN classifiers – Application to remote-sensing image classification?

Author

Adam Jóźwik; Sebastiano Serpico; Fabio Roli

Publisher

Elsevier Science; Elsevier ; Elsevier BV (ISSN 0167-8655)

Published

1998

Language

EN

Field

Computer Science (Physical Sciences)