Abstract | ||
---|---|---|
In the paper we present a new framework for improving classifiers learned from imbalanced data. This framework integrates the SPIDER method for selective data pre-processing with the Ivotes ensemble. The goal of such integration is to obtain improved balance between the sensitivity and specificity for the minority class in comparison to a single classifier combined with SPIDER, and to keep overall accuracy on a similar level. The IIvotes framework was evaluated in a series of experiments, in which we tested its performance with two types of component classifiers (tree- and rule-based). The results show that IIvotes improves evaluation measures. They demonstrated advantages of the abstaining mechanism (i.e., refraining from predictions by component classifiers) in IIvotes rule ensembles. |
Year | Venue | Keywords |
---|---|---|
2010 | RSCTC | iivotes framework,spider method,evaluation measure,ivotes ensemble,component classifier,selective data,new framework,abstaining mechanism,imbalanced data,selective pre-processing,iivotes rule ensemble,rule based |
Field | DocType | Volume |
Improved balance,Importance sampling,Pattern recognition,Random subspace method,Computer science,Artificial intelligence,Classifier (linguistics),Machine learning | Conference | 6086 |
ISSN | ISBN | Citations |
0302-9743 | 3-642-13528-5 | 31 |
PageRank | References | Authors |
1.09 | 9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jerzy Błaszczyński | 1 | 277 | 13.20 |
Magdalena Deckert | 2 | 46 | 2.71 |
Jerzy Stefanowski | 3 | 1653 | 139.25 |
Szymon Wilk | 4 | 461 | 40.94 |