Novelty detection employing an L2 optimal non-parametric density estimator

被引：27

作者：

He, C ^{[1
]}

Girolami, M ^{[1
]}

机构：

[1] Univ Glasgow, Dept Comp Sci, Bioinformat Res Ctr, Glasgow G12 8QQ, Lanark, Scotland

来源：

PATTERN RECOGNITION LETTERS | 2004年 / 25卷 / 12期

关键词：

reduced set density estimator (RSDE); novelty detection; binary classification;

D O I：

10.1016/j.patrec.2004.05.004

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

This paper considers the application of a recently proposed L, optimal non-parametric reduced set density estimator to novelty detection and binary classification and provides empirical comparisons with other forms of density estimation as well as support vector machines. (C) 2004 Elsevier B.V. All rights reserved.

引用

页码：1389 / 1397

页数：9

共 22 条

[1]

[Anonymous], 1958, INTRO MULTIVARIATE S

[2]

BARNETT V, 1977, OUTLIERS STAT DATA

[3]

Campbell C, 2001, ADV NEUR IN, V13, P395

[4]

Efron B., 1994, INTRO BOOTSTRAP, DOI DOI 10.1201/9780429246593

[5]

Probability density estimation from optimally condensed data samples [J].

Girolami, M ;

He, C .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (10) :1253-1264

[6]

The accuracy and the computational complexity of a multivariate binned kernel density estimator [J].

Holmström, L .

JOURNAL OF MULTIVARIATE ANALYSIS, 2000, 72 (02) :264-309

[7]

JUDGE GG, 1988, INTRO THEORY PRACT

[8]

MCLACHLAN G., 2000, WILEY SER PROB STAT, DOI 10.1002/0471721182

[9]

BASIC PRINCIPLES OF ROC ANALYSIS [J].

METZ, CE .

SEMINARS IN NUCLEAR MEDICINE, 1978, 8 (04) :283-298

[10]

Density-based multiscale data condensation [J].

Mitra, P ;

Murthy, CA ;

Pal, SK .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (06) :734-747

← 1 2 3 →