Logo image
An Ensemble Imbalanced Data Classification Algorithm Based on Random k-Rank Nearest Neighbor Rules
Journal article   Open access

An Ensemble Imbalanced Data Classification Algorithm Based on Random k-Rank Nearest Neighbor Rules

怡欣 沈 and Subhash C Bagui
Advances in Applied Mathematics, Vol.9(5), pp.622-629
2020

Metrics

Abstract

Aiming at the problem of imbalanced data classification, in order to improve the low classification accuracy of minority class samples in binary classification tasks, this paper proposes a random rank k-nearest neighbor ensemble learning algorithm, REKRNN. This method applies the rank k-nearest neighbor algorithm to the Bagging ensemble learning framework, and uses hybrid resampling and random subspace method to balance the training set and increase the diversity of base learners. Simulation experiments show that the algorithm performs well in handling imbalanced data classification tasks. In this article, a random ensemble k-RNN algorithm called REKRNN is proposed to deal with the imbalanced data classification. The algorithm incorporates the k-rank nearest neighbor classifier into the frame of Bagging algorithm. At the same time, resampling techniques and random feature method are applied to deal with the imbalanced issue. We observe that the proposed method performed remarkably well on different imbalanced dataset.
url
An Ensemble Imbalanced Data Classification Algorithm Based on Random k-Rank Nearest Neighbor RulesView
Published (Version of record)link to article Open

Related links

Details

Logo image