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.

This data was imported from Web of Science (Lite):

Authors: Shenfield, A., Rostami, S. and IEEE


Pages: 217-224

The data on this page was last updated at 04:57 on May 23, 2019.