The nearest neighbor rule (NN) is one of the most powerful yet simple non parametric classification techniques. However, it is time consuming and it is very ...

In this paper, we propose a new editing and condensing method. Our method combines the Rough Set theory and the Compact Sets structuralizations to obtain a ...

Maximum Similarity Graphs are the basis for several prototype selection methods, such as [4][5] [6] , and offers several advantages to data analysis. They do ...

Two new editing methods based on maximum similarity graphs are proposed, which show the high quality performance of these methods according to classifier ...

To overcome this problem, we propose two new editing methods based on maximum similarity graphs. Numerical experiments in several databases show the high ...

To over- come this problem, we propose two new editing methods based on maximum similarity graphs. Numerical experiments in several databases show the high.

We compare eleven methods for finding prototypes upon which to base the nearest. Ž prototype classifier. Four methods for prototype selection are discussed: ...

The method is based on retaining examples which are near to the decision boundary, while eliminating the rest. The prototype set thus selected is a subset of ...

This paper introduces an attribute and case selection algorithm using a hybrid Rough Set Theory and naturally inspired approach to improve the NN performance.

Feb 29, 2024 · This paper introduced a novel prototype learning based robust open-set node classification method to learn an open-set classifier from graphs ...