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

Authors: Shenfield, A. and Rostami, S.

Start date: 23 August 2017

This data was imported from Scopus:

Authors: Shenfield, A. and Rostami, S.

Journal: 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2017

ISBN: 9781467389884

DOI: 10.1109/CIBCB.2017.8058553

© 2017 IEEE. This paper proposes a novel multi-objective optimisatìon 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 [41] 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 significantiy outperform a standard feed-forward ANN with respect to minority class recognition at the cost of slightiy worse performance in terms of overall classification accuracy.

The data on this page was last updated at 04:56 on March 21, 2019.