On the reduction of the nearest-neighbor variation for more accurate classification and error estimates

被引：4
作者：
Djouadi, A [1 ]
机构：
[1] Lucent Technol, Columbus, OH 43213 USA
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1998年 / 20卷 / 05期
关键词：
nearest-neighbor risk; nearest-neighbor classifier; Bayes error; asymptotic risk; risk estimation;
D O I：
10.1109/34.682188
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In designing the nearest-neighbor (NN) classifier, a method is presented to produce a finite sample size risk close to the asymptotic one. It is based on an attempt to eliminate the first-order effects of the sample size, as well as all higher odd terms. This method uses the 2-NN rule without the rejection option and utilizes a polarization scheme. Simulation results are included as a means of verifying this analysis.
引用
收藏
页码：567 / 571
页数：5
相关论文
共 8 条
[1]   WEIGHTED NEAREST NEIGHBOR RULE FOR CLASS DEPENDENT SAMPLE SIZES [J].
BROWN, TA ;
KOPLOWITZ, J .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1979, 25 (05) :617-619
[2]   NEAREST NEIGHBOR PATTERN CLASSIFICATION [J].
COVER, TM ;
HART, PE .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1967, 13 (01) :21-+
[3]   NEW ERROR BOUNDS WITH THE NEAREST NEIGHBOR RULE [J].
DEVIJVER, PA .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1979, 25 (06) :749-753
[4]  
Duda R. O., 1973, PATTERN CLASSIFICATI
[5]   AN OPTIMAL GLOBAL NEAREST NEIGHBOR METRIC [J].
FUKUNAGA, K ;
FLICK, TE .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (03) :314-318
[6]   THE 2-NN RULE FOR MORE ACCURATE NN RISK-ESTIMATION [J].
FUKUNAGA, K ;
FLICK, TE .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1985, 7 (01) :107-112
[7]  
Short R. D., 1980, Proceedings of the 5th International Conference on Pattern Recognition, P81
[8]   THE OPTIMAL DISTANCE MEASURE FOR NEAREST NEIGHBOR CLASSIFICATION [J].
SHORT, RD ;
FUKUNAGA, K .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1981, 27 (05) :622-627
1