Classifier design using nearest neighbor samples
Yoshihiro Mitani, Yoshihiko Hamamoto · 2002
A considerable amount of effort has been devoted to design a classifier in practical situations. In this paper, a simple nonparametric classifier is proposed. The proposed classifier uses nearest neighbor training samples from a pattern to be classified and its performance is compared with that of the k-NN classifier in terms of the error rate, particularly in small training sample size situations. Experimental results show that the proposed classifier is promising in practical situations.