Paper Info
Title
Ordinal Evolutionary Artificial Neural Networks For Solving An Imbalanced Liver Transplantation Problem
Abstract
Ordinal regression considers classification problems where there exists a natural ordering among the categories. In this learning setting, thresholds models are one of the most used and successful techniques. On the other hand, liver transplantation is a widely-used treatment for patients with a terminal liver disease. This paper considers the survival time of the recipient to perform an appropriate donor-recipient matching, which is a highly imbalanced classification problem. An artificial neural network model applied to ordinal classification is used, combining evolutionary and gradient-descent algorithms to optimize its parameters, together with an ordinal over-sampling technique. The evolutionary algorithm applies a modified fitness function able to deal with the ordinal imbalanced nature of the dataset. The results show that the proposed model leads to competitive performance for this problem.
Year
DOI
Venue
2016
10.1007/978-3-319-32034-2_38
HYBRID ARTIFICIAL INTELLIGENT SYSTEMS
Keywords
Field
DocType
Ordinal regression, Artificial neural networks, Imbalanced classification, Liver transplantation, Donor-recipient matching
Artificial neural network model,Evolutionary algorithm,Existential quantification,Computer science,Ordinal number,Fitness function,Ordinal regression,Artificial intelligence,Artificial neural network,Machine learning,Liver transplantation
Conference
Volume
ISSN
Citations 
9648
0302-9743
2
PageRank 
References 
Authors
0.37
16
5
Name
Order
Citations
PageRank
M. Dorado-Moreno1133.08
María Pérez-Ortiz26112.51
M. D. Ayllón-Terán3130.89
Pedro Antonio Gutiérrez443347.30
César Hervás-Martínez579678.92