Improving the Error Back-Propagation Algorithm for Imbalanced Data Sets

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...

Full description

Saved in:
Bibliographic Details
Published in:International JOURNAL OF CONTENTS Vol. 8; no. 2; pp. 7 - 12
Main Author: Oh, Sang-Hoon
Format: Journal Article
Language:English
Published: 한국콘텐츠학회(IJOC) 28.06.2012
한국콘텐츠학회
Subjects:
컴퓨터학
Error Back-Propagation
Error Function
Mammography
Imbalanced Data
ISSN:1738-6764, 2093-7504
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. KCI Citation Count: 0
Bibliography:G704-SER000010179.2012.8.2.014
www.koreacontents.or.kr
ISSN:1738-6764
2093-7504
DOI:10.5392/IJoC.2012.8.2.007