Abstract | ||
---|---|---|
•We propose an undersampling approach for imbalanced data classification based on information-theoretic learning, termed RIUS.•RIUS preserves the relevant structure of the majority class with a smaller number of samples.•RIUS captures the data structure beyond second-order statistics.•We also enhance the RIUS performance with a clustering-based stage, which yields to our CRIUS approach. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.neucom.2021.01.033 | Neurocomputing |
Keywords | DocType | Volume |
Information theoretic learning,Imbalanced data,Undersampling,Binary classification | Journal | 436 |
ISSN | Citations | PageRank |
0925-2312 | 1 | 0.35 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
J. Hoyos-Osorio | 1 | 1 | 0.35 |
Andrés Álvarez-Meza | 2 | 25 | 2.46 |
G. Daza-Santacoloma | 3 | 1 | 0.35 |
A. Orozco-Gutierrez | 4 | 1 | 0.35 |
G. Castellanos-Dominguez | 5 | 2 | 2.09 |