Multi-objective evolution of artificial neural networks in multi-class medical diagnosis problems with class imbalance

SHENFIELD, Alex and ROSTAMI, Shahin (2017). Multi-objective evolution of artificial neural networks in multi-class medical diagnosis problems with class imbalance. In: CIBCB 2017 : IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, Manchester, 23-25 August 2017. (In Press)

[img]
Preview
PDF
cibcb2017_fetal_ctg.pdf - Submitted Version
Available under License All rights reserved.

Download (335kB) | Preview
Official URL: http://cibcb2017.org/

Abstract

This paper proposes a novel multi-objective optimisation approach to solving both the problem of finding good structural and parametric choices in an ANN and the problem of training a classifier with a heavily skewed data set. The state-of-the-art CMA-PAES-HAGA multi-objective evolutionary algorithm is used to simultaneously optimise the structure, weights, and biases of a population of ANNs with respect to not only the overall classification accuracy, but the classification accuracies of each individual target class. The effectiveness of this approach is then demonstrated on a real-world multi-class problem in medical diagnosis (classification of fetal cardiotocogorams) where more than 75% of the data belongs to the majority class and the rest to two other minority classes. The optimised ANN is shown to significantly outperform a standard feed-forward ANN with respect to minority class recognition at the cost of slightly worse performance in terms of overall classification accuracy.

Item Type: Conference or Workshop Item (Paper)
Research Institute, Centre or Group: Cultural Communication and Computing Research Institute > Communication and Computing Research Centre
Depositing User: Alex Shenfield
Date Deposited: 24 Jul 2017 12:42
Last Modified: 24 Jul 2017 21:45
URI: http://shura.shu.ac.uk/id/eprint/16213

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics