To Combat Multi-Class Imbalanced Problems by Means of Over-Sampling Techniques

By Lida Abdi, Sattar Hashemi. IEEE Transactions on Knowledge and Data Engineering, 2016

363 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary (2018, methodology): “One example is the Malanahobis distance that creates an elliptic area of influence that could be better suited in case of overlapping (Abdi & Hashemi, 2016).”
Learning from imbalanced data: open challenges and future directions (2016, background): “Simple re-balancing towards the biggest or smallest class is not a proper approach [1,15].”
Addressing the issue of digital mapping of soil classes with imbalanced class observations (2019, methodology): “Data-level solutions are resampling techniques such as random over- and under-sampling for manipulating the observed data to become as close to a balanced distribution as possible (Chawla et al., 2002; Abdi and Hashemi, 2016).”
Multi-head CNN-RNN for multi-time series anomaly detection: An industrial case study (2019, methodology): “Hence, over-sampling [55] and under-sampling [56] techniques are usually used to balance the number of instances of both classes.”
Binary relevance for multi-label learning: an overview (2018, methodology): “Next, a tri-class classi ﬁ er g : X × { 0 , + 1 , + 2 } (cid:3)→ R can be induced from D tri jk by applying a multi-class imbalance learning algorithm M I [59–61], i.e., g M I ( D tri jk ).”