DocumentCode :
2332424
Title :
An adaptive nearest neighbor algorithm for classification
Author :
Wang, Ji-Gang ; Neskovic, Predrag ; Cooper, Leon N.
Author_Institution :
Dept. of Phys., Brown Univ., Providence, RI, USA
Volume :
5
fYear :
2005
fDate :
18-21 Aug. 2005
Firstpage :
3069
Abstract :
The k-nearest neighbor rule is one of the simplest and most attractive pattern classification algorithms. It can be interpreted as an empirical Bayes´ classifier based on the estimated a posteriori probabilities from the k-nearest neighbors. The performance of the k-nearest neighbor rule relies on the locally constant a posteriori probability assumption. This assumption, however, becomes problematic in high dimensional spaces due to the curse of dimensionality. In this paper we introduce a locally adaptive nearest neighbor rule. Instead of using the Euclidean distance to locate the nearest neighbors, the proposed method takes into account the effective influence size of each training example and the statistical confidence with which the label of each training example can be trusted. We test the new method on real-world benchmark datasets and compare it with the standard k-nearest neighbor rule and the support vector machines. The experimental results confirm the effectiveness of the propose method.
Keywords :
adaptive systems; pattern classification; statistical analysis; adaptive nearest neighbor algorithm; curse of dimensionality; k-nearest neighbor; locally adaptive nearest neighbor; pattern classification algorithms; statistical confidence; Benchmark testing; Classification algorithms; Electronic mail; Euclidean distance; Nearest neighbor searches; Neural networks; Pattern classification; Physics; Support vector machine classification; Support vector machines; Classification; curse of dimensionality; nearest neighbor rule; statistical confidence;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
Type :
conf
DOI :
10.1109/ICMLC.2005.1527469
Filename :
1527469
Link To Document :
بازگشت