Oversampling for Imbalanced Learning Based on K-Means and SMOTE

Published in

Information Sciences(2017)

External Links:

Generate Graph DownloadPDF

TL;DR

This work presents a simple and effective oversampling method based on k-means clustering and SMOTE (synthetic minority oversampled technique), which avoids the generation of noise and effectively overcomes imbalances between and within classes.

Authors

F. Bação

2 papers

F. Last

1 papers

Georgios Douzas

1 papers

References52 items

Clustering-based undersampling in class-imbalanced data

Noise Reduction A Priori Synthetic Over-Sampling for class imbalanced data sets

An empirical comparison of techniques for the class imbalance problem in churn prediction

Self-Organizing Map Oversampling (SOMO) for imbalanced data set learning

CURE-SMOTE algorithm and hybrid algorithm for feature selection and parameter optimization based on random forests

Oversampling for Imbalanced Learning Based on K-Means and SMOTE

Published in

Information Sciences(2017)

External Links:

Generate Graph DownloadPDF

TL;DR

Authors

F. Bação

2 papers

F. Last

1 papers

Georgios Douzas

1 papers

References52 items

Clustering-based undersampling in class-imbalanced data

Noise Reduction A Priori Synthetic Over-Sampling for class imbalanced data sets

An empirical comparison of techniques for the class imbalance problem in churn prediction

Self-Organizing Map Oversampling (SOMO) for imbalanced data set learning

CURE-SMOTE algorithm and hybrid algorithm for feature selection and parameter optimization based on random forests

Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning

Ordering-based pruning for improving the performance of ensembles of classifiers in the framework of imbalanced datasets

A bi-directional sampling based on K-means method for imbalance text classification

Adaptive semi-unsupervised weighted oversampling (A-SUWO) for imbalanced datasets

Diversity techniques improve the performance of the best imbalance learning ensembles

A new cluster-based oversampling method for improving survival prediction of hepatocellular carcinoma patients

SMOTE-IPF: Addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering

Assessment Metrics for Imbalanced Learning

Analysing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approaches

A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches

Scikit-learn: Machine Learning in Python

Web-scale k-means clustering

COG: local decomposition for rare class analysis

Learning from Imbalanced Data

Safe-Level-SMOTE: Safe-Level-Synthetic Minority Over-Sampling TEchnique for Handling the Class Imbalanced Problem

Machine Learning from Imbalanced Data Sets 101

Automatically countering imbalance and its empirical relationship to cost

Robustness of learning techniques in handling class noise in imbalanced datasets

Statistical Comparisons of Classifiers over Multiple Data Sets

Combating imbalance in network intrusion datasets

Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning

Learning with Class Skews and Small Disjuncts

Class imbalances versus small disjuncts

Editorial: special issue on learning from imbalanced data sets

A study of the behavior of several methods for balancing machine learning training data

The Problem of Overfitting

A Multiple Resampling Method for Learning from Imbalanced Data Sets

Greedy function approximation: A gradient boosting machine.

MetaCost: a general method for making classifiers cost-sensitive

Discriminatory Analysis - Nonparametric Discrimination: Consistency Properties

Concept Learning and the Problem of Small Disjuncts

Generalized Linear Models

The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance

THE DARWIN CELEBRATION AT CAMBRIDGE.

Imbalanced classification in sparse and large behaviour datasets

Hellinger distance decision trees are robust and skew-insensitive

KEEL Data-Mining Software Tool: Data Set Repository, Integration of Algorithms and Experimental Analysis Framework

Cost-Sensitive Learning vs. Sampling: Which is Best for Handling Unbalanced Classes with Unequal Error Costs?

Handling imbalanced datasets: A review

Data Mining for Imbalanced Datasets: An Overview

Design of experiments for the NIPS 2003 variable selection benchmark

SMOTE: Synthetic Minority Over-sampling Technique

Using Unsupervised Learning to Guide Resampling in Imbalanced Data Sets

A Simple Sequentially Rejective Multiple Test Procedure

Some methods for classification and analysis of multivariate observations

Some methods for classi cation and analysis of multivariate observations

To obtain a measure of density, divide each cluster’s number of minority instances by its average minority distance raised to the power of the number of features

Field of Study

Computer ScienceMathematics

Journal Information

Name

Inf. Sci.

Page

122499

Volume

719

Venue Information

Name

Information Sciences

Type

journal

URL

http://www.sciencedirect.com/science/journal/00200255

Alternate Names

Information Scientist
Inf Sci