Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 허선 | - |
dc.date.accessioned | 2021-07-27T02:16:48Z | - |
dc.date.available | 2021-07-27T02:16:48Z | - |
dc.date.issued | 2020-01 | - |
dc.identifier.citation | JOURNAL OF CLASSIFICATION, v. 38, Issue 1, Page. 2-15 | en_US |
dc.identifier.issn | 0176-4268 | - |
dc.identifier.uri | https://link.springer.com/article/10.1007/s00357-019-09359-9 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/163278 | - |
dc.description.abstract | Classifiers for a highly imbalanced dataset tend to bias in majority classes and, as a result, the minority class samples are usually misclassified as majority class. To overcome this, a proper undersampling technique that removes some majority samples can be an alternative. We propose an efficient and simple undersampling method for imbalanced datasets and show that the proposed method outperforms others with respect to four different performance measures by several illustrative experiments, especially for highly imbalanced datasets. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | SPRINGER | en_US |
dc.subject | Imbalanced class problem | en_US |
dc.subject | undersampling | en_US |
dc.subject | membership probability | en_US |
dc.subject | information loss | en_US |
dc.title | A Membership Probability Based Undersampling Algorithm for Imbalanced Data | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1007/s00357-019-09359-9 | - |
dc.relation.page | 1-14 | - |
dc.relation.journal | JOURNAL OF CLASSIFICATION | - |
dc.contributor.googleauthor | Ahn, Gilseung | - |
dc.contributor.googleauthor | Park, You-Jin | - |
dc.contributor.googleauthor | Hur, Sun | - |
dc.relation.code | 2020056550 | - |
dc.sector.campus | E | - |
dc.sector.daehak | COLLEGE OF ENGINEERING SCIENCES[E] | - |
dc.sector.department | DEPARTMENT OF INDUSTRIAL AND MANAGEMENT ENGINEERING | - |
dc.identifier.pid | hursun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.