ABSTRACT
The machine learning field has grown considerably in the last years. There are, however, some problems still to be solved. The characteristics of the training sets, for instance, are known to affect the classifiers performance. Here, and inspired by medical applications, we are interested in studying datasets that are both ordinal and imbalanced. Ordinal datasets present labels where only the relative ordering between different values is significant. Imbalanced datasets have very different quantity of examples per class.
Building upon our previous work, we make three new contributions, (1) extend the number of classifiers, (2) evaluate two techniques to balance intermediate train sets in binary decomposition methods (often used in multi-class contexts and ordinal ones in particular), and (3) propose a new, iterative, classifier-based over-sampling algorithm that we name InCuBAtE. Experiments were made on 6 private datasets, concerning the assessment of response to treatment on oncologic diseases, and 15 public datasets widely used in the literature. When compared with our previous work, results have improved (or remained the same) for 4 of the 6 private datasets and for 11 out of the 15 public datasets.
- S Bessa, I Domingues, J S Cardosos, P Passarinho, P Cardoso, V Rodrigues, and F Lage. 2014. Normal breast identification in screening mammography: a study on 18 000 images. In IEEE International Conference on Bioinformatics and Biomedicine. 325--330.Google ScholarCross Ref
- R Cruz, K Fernandes, J F P Costa, and J S Cardoso. 2017. Constraining Type II Error: Building Intentionally Biased Classifiers. In International Work-Conference on Artificial Neural Networks. Springer, 549--560.Google Scholar
- R Cruz, K Fernandes, J F P Costa, M P Ortiz, and J S Cardoso. 2018. Binary ranking for ordinal class imbalance. Pattern Analysis and Applications (2018), 1--9. Google ScholarDigital Library
- I Domingues, J P Amorim, P H Abreu, H Duarte, and J Santos. 2018. Evaluation of oversampling data balancing techniques in the context of ordinal classification. In IEEE International Joint Conference on Neural Networks. 5691--5698.Google ScholarCross Ref
- E Frank and M Hall. 2001. A Simple Approach to Ordinal Classification. In European Conference on Machine Learning. Springer, 145--156. Google ScholarDigital Library
- P A Gutiérrez, M Pérez-Ortiz, J Sánchez-Monedero, F Fernández-Navarro, and C Hervás-Martínez. 2015. Ordinal regression methods: survey and experimental study. IEEE Transactions on Knowledge and Data Engineering 28, 1 (2015), 127--146. Google ScholarDigital Library
- T Hastie, R Tibshirani, and J H Friedman. 2009. The Elements of Statistical Learning. Springer. 745 pages.Google Scholar
- M Pérez-Ortiz, M Cruz-Ramírez, M D Ayllón-Terán, N Heaton, R Ciria, and C Hervás-Martínez. 2014. An organ allocation system for liver transplantation based on ordinal regression. Applied Soft Computing Journal 14 (2014), 88--98. Google ScholarDigital Library
- M S Santos, P H Abreu, P J García-Laencina, A Simão, and A Carvalho. 2015. A new cluster-based oversampling method for improving survival prediction of hepatocellular carcinoma patients. Journal of Biomedical Informatics 58 (2015), 49--59. Google ScholarDigital Library
Index Terms
- An iterative oversampling approach for ordinal classification
Recommendations
Iterative minority oversampling and its ensemble for ordinal imbalanced datasets
AbstractOrdinal classification of imbalanced datasets is a challenging problem that occurs in many real-world applications. The main challenge is to simultaneously consider the classes ordering and imbalanced distribution. Although the classic synthetic ...
An Empirical Study of Oversampling and Undersampling for Instance Selection Methods on Imbalance Datasets
CIARP 2013: Proceedings, Part I, of the 18th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - Volume 8258Instance selection methods get low accuracy in problems with imbalanced databases. In the literature, the problem of imbalanced databases has been tackled applying oversampling or undersampling methods. Therefore, in this paper, we present an empirical ...
A new oversampling approach based differential evolution on the safe set for highly imbalanced datasets
AbstractOversampling method is used to solve the class imbalanced issues. Some existing oversampling methods do not well remove noisy samples and avoid synthesizing noisy samples. Therefore, we propose a new oversampling approach based differential ...
Highlights- SS_DEBOHID improves diversity of synthesized samples and reduces noisy samples.
- SS_DEBOHID uses the basic strategy of DE to generate samples in the safe area.
- SS_DEBOHID is better than 10 methods on 43 highly imbalanced datasets.
Comments