Conference proceeding
Variable Target Values Neural Network for Dealing with Extremely Imbalanced Datasets
XIV MEDITERRANEAN CONFERENCE ON MEDICAL AND BIOLOGICAL ENGINEERING AND COMPUTING 2016, v 57, pp 519-522
01 Jan 2016
Abstract
An original classification algorithm is proposed for dealing with extremely imbalanced datasets that often appear in biomedical problems. Its originality comes from the way a neural network is trained in order to get a decent hypothesis out of a dataset that comprises of a huge sized majority class and a tiny size minority class. This situation is especially probable when forming machine learning databases describing rare medical conditions. The algorithm is tested on a large dataset in order to predict the risk of preeclampsia in pregnant women. Conventional machine learning algorithms tend to provide poor hypothesis for extremely imbalanced datasets by favoring the majority class. The proposed algorithm is not trained on the basis of the mean squared error objective function and thus avoids the overwhelming effect of the highly asymmetric class sizes. The methodology provides preeclampsia detection rate of 49% and normal case detection rate slightly above 76%.
Metrics
8 Record Views
Details
- Title
- Variable Target Values Neural Network for Dealing with Extremely Imbalanced Datasets
- Creators
- Savvas Karatsiolis - Univ Cyprus, Dept Comp Sci, 1 Univ Ave, CY-1678 Nicosia, CyprusChristos N. Schizas - Univ Cyprus, Dept Comp Sci, 1 Univ Ave, CY-1678 Nicosia, CyprusDov Jaron - School of Biomedical Engineering, Science, and Health Systems (1997-)
- Contributors
- E Kyriacou (Editor)S Christofides (Editor)C S Pattichis (Editor)
- Publication Details
- XIV MEDITERRANEAN CONFERENCE ON MEDICAL AND BIOLOGICAL ENGINEERING AND COMPUTING 2016, v 57, pp 519-522
- Series
- IFMBE Proceedings
- Publisher
- Springer Nature
- Number of pages
- 4
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems; [Retired Faculty]
- Web of Science ID
- WOS:000376283000101
- Scopus ID
- 2-s2.0-84968645083
- Other Identifier
- 991019173559404721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Engineering, Biomedical
- Materials Science, Biomaterials