A New Discernibility Metric and Its Application on Pattern Classification and Feature Evaluation - Artificial Intelligence Applications and Innovations - Part II Access content directly
Conference Papers Year : 2011

A New Discernibility Metric and Its Application on Pattern Classification and Feature Evaluation

Zacharias Voulgaris
  • Function : Author
  • PersonId : 1014223

Abstract

A novel evaluation metric is introduced, based on the Discernibility concept. This metric, the Distance-based Index of Discernibility (DID) aims to provide an accurate and fast mapping of the classification performance of a feature or a dataset. DID has been successfully implemented in a program which has been applied to a number of datasets, a few artificial features and a typical benchmark dataset. The results appear to be quite promising, verifying the initial hypothesis.
Fichier principal
Vignette du fichier
978-3-642-23960-1_4_Chapter.pdf (144.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01571488 , version 1 (02-08-2017)

Licence

Attribution

Identifiers

Cite

Zacharias Voulgaris. A New Discernibility Metric and Its Application on Pattern Classification and Feature Evaluation. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. pp.27-35, ⟨10.1007/978-3-642-23960-1_4⟩. ⟨hal-01571488⟩
152 View
230 Download

Altmetric

Share

Gmail Facebook X LinkedIn More