Modified Reduct: Nearest Neighbor Classification
Naohiro Ishii, Ippei Torii, Yang Bao, Hidekazu Tanaka · 2012
Dimension reduction of data is an important theme as in the data processing and on the web to represent and manipulate higher dimensional data. Rough set developed is fundamental and useful to process higher dimensional data. Reduct in the rough set is a minimal subset of features, which has almost the same discernible power as the entire features in the higher dimensional scheme. Then, there are relations between reducts and their classification classes. Here, we develop a method which connects reducts and the nearest neighbor method to classify data with higher classification accuracy. To improve the classification ability of reducts, we propose a new modified reduct and its optimization method for the classification with higher accuracy. Then, it is shown that the modified reduct improves the classification accuracy, which is followed by the optimized nearest neighbor classification.