OWA-FRPS: A Prototype Selection method based on Ordered Weighted Average Fuzzy Rough Set Theory

Abstract

The Nearest Neighbor (NN) algorithm is a well-known and effective classification algorithm. Prototype Selection (PS), which provides NN with a good training set to pick its neighbors from, is an important topic as NN is highly susceptible to noisy data. Accurate state-of-the-art PS methods are generally slow, which motivates us to propose a new PS method, called OWA-FRPS. Based on the Ordered Weighted Average (OWA) fuzzy rough set model, we express the quality of instances, and use a wrapper approach to decide which instances to select. An experimental evaluation shows that OWA-FRPS is significantly more accurate than state-of-the-art PS methods without requiring a high computational cost.