New clustering methods for interval data

被引：72

作者：

Chavent, Marie

de Carvalho, Francisco de A. T.

Lechevallier, Yves

Verde, Rosanna

机构：

[1] Univ Bordeaux 1, MAB Math Appl Bordeaux, F-33405 Talence, France

[2] Univ Fed Pernambuco, Ctr Informat, BR-50740540 Recife, PE, Brazil

[3] Inst Natl Rech Informat & Automat, F-78153 Le Chesnay, France

[4] Seconda Univ Napoli, Dip Strategie Aziendali & Metodol Quantitat, I-81043 Capua, Italy

来源：

COMPUTATIONAL STATISTICS | 2006年 / 21卷 / 02期

关键词：

dynamic clustering; interval data; distances; prototypes;

D O I：

10.1007/s00180-006-0260-0

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 [统计学]; 070103 [概率论与数理统计]; 0714 [统计学];

摘要：

In this paper we propose two clustering methods for interval data based on the dynamic cluster algorithm. These methods use different homogeneity criteria as well as different kinds of cluster representations (prototypes). Some tools to interpret the final partitions are also introduced. An application of one of the methods concludes the paper.

引用

页码：211 / 229

页数：19

共 20 条

[1]

[Anonymous], 2002, Classification, Clustering, and Data Analysis

[2]

[Anonymous], P 9 INT S ASMDA 99

[3]

BOCK HH, 2000, STUDIES CLASSIFICATI

[4]

BOCK HH, 2001, ICNCB P, P203

[5]

Celeux G., 1989, Classification Automatique Des Donnees

[6]

Chavent M, 2004, STUD CLASS DATA ANAL, P333

[7]

Chavent M., 2003, Rev. Stat. Appl, VLI, P5

[8]

Clustering of interval data based on city-block distances [J].

de Souza, RMCR ;

de Carvalho, FDT .

PATTERN RECOGNITION LETTERS, 2004, 25 (03) :353-365

[9]

DECARVALHO FAT, 1995, ANN OPER RES, V55, P289

[10]

DECARVALHO FAT, 1998, ADV DATA SCI CLASSIF, P391

← 1 2 →