Improving Identification of Difficult Small Classes by Balancing Class Distribution

By Jorma Laurikkala. Conference on Artificial Intelligence in Medicine in Europe, 2001

789 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e51e0633e12f5c037f1e405ccc31c4c50f5ae87f

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Data mining with imbalanced class distributions: concepts and methods (2009, methodology): “Neighborhood Cleaning Rule Neighborhood Cleaning Rule (NCL) [12] uses the Wilson’s Edited Nearest Neighbor Rule (ENN) [13] to remove majority class examples.”
A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data (2021, background): “Also, if a sample belongs to the minority class sample and is misclassified by its three nearest neighbours, then the majority class samples among its neighbours are removed [35].”
Study of the impact of resampling methods for contrast pattern based classifiers in imbalanced databases (2016, methodology): “NCL: Neighborhood Cleaning Rule [51] uses the ENN rule to remove objects from the majority class.”
On the Class Imbalance Problem (2008, background): “NCL uses ENN to remove majority examples, for each example E i in the training set, its three nearest neighbors are found.”
Enhancing the effectiveness and interpretability of decision tree and rule induction classifiers with evolutionary training set selection over imbalanced problems (2009, methodology): “NCL modifies the ENN in order to increase the data cleaning.”
Inverse random under sampling for class imbalance problem and its application to multi-label classification (2012, methodology): “Several heuristic methods are proposed to overcome these limitations including Tomek’s links [12], Condensed Nearest Neighbor Rule (CNN) [13], one-sided selection [1] and Neighborhood Cleaning rule (NCL) [14] are several well-known methods for under-sampling while Synthetic Minority Over-Sampling Te”
A comprehensive data level analysis for cancer diagnosis on imbalanced data (2019, background): “The class label of the removed samples is different from 3 to 5 neighbours [36].”
Local neighbourhood extension of SMOTE for mining imbalanced data (2011, methodology): “Thus, focused methods like SMOTE [1], oneside-sampling [4], NCR [5] or SPIDER [6], which attempt on taking into account internal characteristics of regions around minority class examples were introduced and experimentally verified.”
On the use of MapReduce for imbalanced big data using Random Forest (2014, methodology): “Oversampling methods [11,12,26] aim to balance the class distribution adding to the new dataset instances from the minority class; undersampling methods [22,30,52] try to adjust the class proportion deleting instances from the majority class; and hybrid methods [6] combine the two previous approache”
Data Mining for Imbalanced Datasets: An Overview (2005, background): “(Laurikkala, 2001) proposed Neighborhood Cleaning Rule (NCL) to remove the majority class”
Combating imbalance in network intrusion datasets (2006, background): “Over and under-sampling methodologies have received significant attention to counter the effect of imbalanced datasets [10], [17]–[20].”
Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning (2016, background): “, 1997), (iv) neighbourhood cleaning rule (Laurikkala, 2001), and (v) Tomek links (Tomek, 1976).”