Improving the Error Back-Propagation Algorithm for Imbalanced Data Sets
International Journal of Contents · 28.06.2012 · 8 (2) · 7-12
DOI: 10.5392/ijoc.2012.8.2.007 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Contents, erschienen am 28.06.2012. Verfasst von Sang-Hoon Oh. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 12 Literaturangaben.
Abstract (Originalsprache)
Imbalanced data sets are difficult to be classified since most classifiers are developed based on the assumption that class distributions are well-balanced. In order to improve the error back-propagation algorithm for the classification of imbalanced data sets, a new error function is proposed. The error function controls weight-updating with regards to the classes in which the training samples are. This has the effect that samples in the minority class have a greater chance to be classified but samples in the majority class have a less chance to be classified. The proposed method is compared with the two-phase, threshold-moving, and target node methods through simulations in a mammography data set and the proposed method attains the best results.
Zitieren
APA
Oh, S. (2012). Improving the Error Back-Propagation Algorithm for Imbalanced Data Sets. International Journal of Contents, 8(2), 7-12. https://doi.org/10.5392/ijoc.2012.8.2.007
Vancouver
Oh S. Improving the Error Back-Propagation Algorithm for Imbalanced Data Sets. International Journal of Contents. 2012;8(2):7-12. doi:10.5392/ijoc.2012.8.2.007
BibTeX
@article{Oh2012,
author = {Oh, Sang-Hoon},
title = {Improving the Error Back-Propagation Algorithm for Imbalanced Data Sets},
journal = {International Journal of Contents},
year = {2012},
volume = {8},
number = {2},
pages = {7--12},
doi = {10.5392/ijoc.2012.8.2.007}
}
EUVIMED