Label noise filtering techniques to improve monotonic classification

TitleLabel noise filtering techniques to improve monotonic classification
Publication TypeJournal Article
Year of Publication2019
AuthorsCano, J. R., Luengo J., and García S.
JournalNeurocomputing
Volume353
Pagination83-95
Date Published08/2019
ISSN0925-2312
KeywordsMonotonic classification, Noise filtering, Ordinal classification, Preprocessing
Abstract

The monotonic ordinal classification has increased the interest of researchers and practitioners within machine learning community in the last years. In real applications, the problems with monotonicity constraints are very frequent. To construct predictive monotone models from those problems, many classifiers require as input a data set satisfying the monotonicity relationships among all samples. Changing the class labels of the data set (relabeling) is useful for this. Relabeling is assumed to be an important building block for the construction of monotone classifiers and it is proved that it can improve the predictive performance. In this paper, we will address the construction of monotone datasets considering as noise the cases that do not meet the monotonicity restrictions. For the first time in the specialized literature, we propose the use of noise filtering algorithms in a preprocessing stage with a double goal: to increase both the monotonicity index of the models and the accuracy of the predictions for different monotonic classifiers. The experiments are performed over 12 datasets coming from classification and regression problems and show that our scheme improves the prediction capabilities of the monotonic classifiers instead of being applied to original and relabeled datasets. In addition, we have included the analysis of noise filtering process in the particular case of wine quality classification to understand its effect in the predictive models generated.

Notes

TIN2014-57251-P; TIN2017-89517-P; TEC2015-69496-R; BigDaP-TOOLS

URLhttp://www.sciencedirect.com/science/article/pii/S092523121930325X
DOI10.1016/j.neucom.2018.05.131
Fichero: