Enrichment Procedures for Soft Clusters: A Statistical Test and its Applications
2010) Enrichment Procedures for Soft Clusters: A Statistical Test and its Applications. Technical Report TR-10-02, Computer Science, Virginia Tech. (
Clusters, typically mined by modeling locality of attribute spaces, are often evaluated for their ability to demonstrate ‘enrichment’ of categorical features. A cluster enrichment procedure evaluates the membership of a cluster for significant representation in pre-defined categories of interest. While classical enrichment procedures assume a hard clustering deﬁnition, in this paper we introduce a new statistical test that computes enrichments for soft clusters. We demonstrate an application of this test in reﬁning and evaluating soft clusters for classification of remotely sensed images.
|Item Type:||Departmental Technical Report|
|Keywords:||enrichment, soft clusters|
|Subjects:||Computer Science > Numerical Analysis|
|Deposited By:||Administrator, Eprints|
|Deposited On:||12 February 2010|