Title :
A bootstrap technique for nearest neighbor classifier design
Author :
Hamamoto, Yoshihiko ; Uchimura, Shunji ; Tomita, Shingo
Author_Institution :
Fac. of Eng., Yamaguchi Univ., Ube, Japan
fDate :
1/1/1997 12:00:00 AM
Abstract :
A bootstrap technique for nearest neighbor classifier design is proposed. Our primary interest in designing a classifier is in small training sample size situations. Conventional bootstrapping techniques sample the training samples with replacement. On the other hand, our technique generates bootstrap samples by locally combining original training samples. The nearest neighbor classifier is designed on the bootstrap samples and is tested on the test samples independent of training samples. The performance of the proposed classifier is demonstrated on three artificial data sets and one real data set. Experimental results show that the nearest neighbor classifier designed on the bootstrap samples outperforms the conventional k-NN classifiers as well as the edited 1-NN classifiers, particularly in high dimensions
Keywords :
pattern classification; bootstrap technique; edited 1-NN classifiers; k-NN classifiers; nearest neighbor classifier design; Computer Society; Electronic mail; Error analysis; Euclidean distance; Nearest neighbor searches; Testing;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on