Adjusted Concordance Index: an Extensionl of the Adjusted Rand Index to Fuzzy Partitions

被引：13

作者：

D'Ambrosio, Antonio ^{[1
]}

Amodio, Sonia ^{[2
]}

Iorio, Carmela ^{[3
]}

Pandolfo, Giuseppe ^{[3
]}

Siciliano, Roberta ^{[3
]}

机构：

[1] Univ Naples Federico II, Dept Econ & Stat, Naples, Italy

[2] Leiden Univ, Med Ctr, Dept Med Stat & Bioinformat, Leiden, Netherlands

[3] Univ Naples Federico II, Dept Ind Engn, Naples, Italy

来源：

JOURNAL OF CLASSIFICATION | 2021年 / 38卷 / 01期

关键词：

Clustering; Cluster validity; Fuzzy partitions; Normalized degree of concordance; SIMILARITY INDEXES; AGREEMENT; JACCARD;

D O I：

10.1007/s00357-020-09367-0

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

In comparing clustering partitions, the Rand index (RI) and the adjusted Rand index (ARI) are commonly used for measuring the agreement between partitions. Such external validation indexes can be used to quantify how close the clusters are to a reference partition (or to prior knowledge about the data) by counting classified pairs of elements. To evaluate the solution of a fuzzy clustering algorithm, several extensions of the Rand index and other similarity measures to fuzzy partitions have been proposed. An extension of the ARI for fuzzy partitions based on thenormalized degree of concordanceis proposed. The performance of the proposed index is evaluated through Monte Carlo simulation studies.

引用

页码：112 / 128

页数：17

共 48 条

[1] On similarity indices and correction for chance agreement [J].