Kernel density estimation with adaptive varying window size

被引：60

作者：

Katkovnik, V

Shmulevich, I

机构：

[1] Univ Texas, MD Anderson Canc Ctr, Houston, TX 77030 USA

[2] Kwangju Inst Sci & Technol, Kwangju, South Korea

来源：

PATTERN RECOGNITION LETTERS | 2002年 / 23卷 / 14期

关键词：

non-parametric; kernel; density estimation; parzen; ICI rule;

D O I：

10.1016/S0167-8655(02)00127-7

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new method of kernel density estimation with a varying adaptive window size is proposed. It is based on the so-called intersection of confidence intervals (10) rule. Several examples of the proposed method are given for different types of densities and the quality of the adaptive density estimate is assessed by means of numerical simulations. (C) 2002 Elsevier Science B.V. All rights reserved.

引用

页码：1641 / 1648

页数：8

共 21 条

[1] ON BANDWIDTH VARIATION IN KERNEL ESTIMATES - A SQUARE ROOT LAW [J].

ABRAMSON, IS .

ANNALS OF STATISTICS, 1982, 10 (04) :1217-1223

[2] VARIABLE KERNEL ESTIMATES OF MULTIVARIATE DENSITIES [J].

BREIMAN, L ;

MEISEL, W ;

PURCELL, E .

TECHNOMETRICS, 1977, 19 (02) :135-144

[3] ESTIMATION OF A MULTIVARIATE DENSITY [J].

CACOULLOS, T .

ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 1966, 18 (02) :179-+

[4]

CHIU ST, 1992, BIOMETRIKA, V79, P771, DOI 10.2307/2337233

[5]

Fan J., 1996, Local Polynomial Modelling and Its Applications: Monographs on Statistics and Applied Probability

[6]

Fukunaga K., 1990, STAT PATTERN RECOGNI

[7]

Goldenshluger A., 1997, MATH METHODS STAT, V6, P135

[8]

HALL P, 1991, BIOMETRIKA, V78, P263

[9] A new method for varying adaptive bandwidth selection [J].

Katkovnik, V .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1999, 47 (09) :2567-2571

[10]

KATKOVNIK V, 2000, EOS SPIE S IM SIGN P

← 1 2 3 →