Journal ArticleDOI
Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
Georgios Douzas,Fernando Bacao +1 more
Reads0
Chats0
TLDR
Geometric SMOTE (G-SMOTE) is proposed as a enhancement of the SMOTE data generation mechanism and empirical results show a significant improvement in the quality of the generated data when G- SMOTE is used as an oversampling algorithm.About:
This article is published in Information Sciences.The article was published on 2019-10-01. It has received 102 citations till now.read more
Citations
More filters
Journal ArticleDOI
RCSMOTE: Range-Controlled synthetic minority over-sampling technique for handling the class imbalance problem
TL;DR: An improved SMOTE-based method, namely Range-Controlled SMOTE (RCSMOTE), which targets all three problems simultaneously and overcomes the above-mentioned problems of SMOTE.
Journal ArticleDOI
LoRAS: an oversampling approach for imbalanced datasets
TL;DR: To explain the success of the algorithm, a mathematical framework is constructed to prove that LoRAS oversampling technique provides a better estimate for the mean of the underlying local data distribution of the minority class data space.
Journal ArticleDOI
RSMOTE: A self-adaptive robust SMOTE for imbalanced problems with label noise
TL;DR: In RSMOTE, relative density has been introduced to measure the local density of every minority sample, and the non-noisy minority samples are divided into the borderline samples and safe samples adaptively basing their distinguishing characteristics of relative density.
Posted Content
DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data.
TL;DR: DeepSMOTE as discussed by the authors is a novel oversampling algorithm for deep learning models, which consists of three major components: an encoder/decoder framework, SMOTE-based over-sampling, and a dedicated loss function that is enhanced with a penalty term.
Journal ArticleDOI
Multi-class imbalanced big data classification on Spark
TL;DR: This paper proposes the first compound framework for dealing with multi-class big data problems, addressing at the same time the existence of multiple classes and high volumes of data, and proposes an efficient implementation of the discussed algorithm on Apache Spark.
References
More filters
Journal ArticleDOI
Book Review: C4.5: Programs for Machine Learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993
TL;DR: In his new book, C4.5: Programs for Machine Learning, Quinlan has put together a definitive, much needed description of his complete system, including the latest developments, which will be a welcome addition to the library of many researchers and students.
Journal ArticleDOI
Analysing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approaches
TL;DR: This experimental study will include several well-known algorithms from the literature such as decision trees, support vector machines and instance-based learning, with the intention of obtaining global conclusions from different classification paradigms.
Journal ArticleDOI
Resampling-Based Ensemble Methods for Online Class Imbalance Learning
TL;DR: This paper gives the first comprehensive analysis of class imbalance in data streams, in terms of data distributions, imbalance rates and changes in class imbalance status, and proposes two new ensemble methods that maintain both OOB and UOB with adaptive weights for final predictions, called WEOB1 and WEOb2.
Journal ArticleDOI
AnO(n logn) algorithm for the all-nearest-neighbors Problem
TL;DR: This work gives anO(n logn) algorithm for the all-nearest-neighbors problem, for fixed dimensionk and fixed metricLq, which is optimal up to a constant factor.
Journal ArticleDOI
DBSMOTE: Density-Based Synthetic Minority Over-sampling TEchnique
TL;DR: A new over-sampling technique called DBSMOTE is proposed, which relies on a density-based notion of clusters and is designed to over-sample an arbitrarily shaped cluster discovered by DBSCAN.