Open AccessA Quantile K-means Bayes Approach to Classification for Imbalanced Data
Author(s) -
Yanzhu Hu,
Xudong Zhao,
Song Wang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/782/4/042051
Subject(s) - naive bayes classifier , classifier (uml) , computer science , quantile , artificial intelligence , bayes classifier , bayes' theorem , machine learning , data mining , data classification , data set , pattern recognition (psychology) , bayesian probability , mathematics , statistics , support vector machine
This paper focuses on the classification of imbalance data. In Machine Learning, a data set is imbalanced when the class proportions are highly skewed. A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. A new approach called Quantile K-means Bayes was proposed to solve the problem. The first focus is on a modified q-classifier. The second focus is on combine the k-means and Bayes algorithm using the data density. The proposed approach is evaluated by 101 benchmark data sets from KEEL collection. A comparison of the proposed approach and other conventional approaches is presented in terms of the G-mean. It can be seen that the proposed approach is able to acquire good performance among the other conventional approaches do. Therefore, this novel approach is an added value for the classification problem for imbalance data.