A STATISTICAL DECISION RULE WITH INCOMPLETE KNOWLEDGE ABOUT CLASSES

被引：111

作者：

DUBUISSON, B

MASSON, M

机构：

[1] Université de Technologie de Compiègne, U.R.A. C.N.R.S., 817 Heuristique et Diagnostic des Systèmes Complexes, 60206 Compiègne Cédex

来源：

PATTERN RECOGNITION | 1993年 / 26卷 / 01期

关键词：

CLASSIFICATION; RULE WITH REJECT OPTION; INCOMPLETE KNOWLEDGE; INCOMPLETE LEARNING SET; DIAGNOSIS;

D O I：

10.1016/0031-3203(93)90097-G

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A statistical decision rule among M classes is presented when the a priori knowledge about classes is not complete: either the number of classes is not the true one, or it is not possible to obtain samples from all the possible classes. The reject option proposed by Chow is extended by defining an ambiguity reject option and a distance reject option. These two types of reject can be defined in a parametric as well as in a non-parametric way. An example is given in R in order to illustrate this rule. This method has been developed essentially to solve diagnostic problems.

引用

页码：155 / 165

页数：11

共 18 条

[1]

CHOW CK, 1970, IEEE T INFORM THEORY, V16, P41, DOI 10.1109/TIT.1970.1054406

[2]

CHOW CK, 1957, RE T EL COMP, P247

[3]

DASARATHY BV, 1980, IEEE T PATTERN ANAL, V2

[4]

DEVIJER P, 1982, PATTERN RECOGNITION

[5] NEW ERROR BOUNDS WITH THE NEAREST NEIGHBOR RULE [J].

DEVIJVER, PA .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1979, 25 (06) :749-753

[6]

DIDAY E, 1976, CLUSTER ANAL DIGITAL

[7] SURVEILLANCE OF A NUCLEAR-REACTOR BY USE OF A PATTERN-RECOGNITION METHODOLOGY [J].

DUBUISSON, B ;

LAVISON, P .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1980, 10 (10) :603-609

[8]

DUBUISSON B, 1987, NUCL SCI TECHNOL, V6, P929

[9]

DUBUISSON B, 1990, SIGNAL PROCESS, V5, P1715

[10]

DUBUISSON B, 1990, DIAGNOSTIC RECONNAIS

← 1 2 →