Ordinal Evolutionary Artificial Neural Networks for Solving an Imbalanced Liver Transplantation Problem

Dorado-Moreno, Manuel; Pérez-Ortiz, María; Ayllón-Terán, M.D.; Gutiérrez, Pedro Antonio; Hervás-Martı́nez, César

doi:10.1007/978-3-319-32034-2_38

Cited by 3 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is especially true when combined with the evolutionary ordinal neural network methodologies (ORNET, IM-ORNET and DIM-ORNET). It can also be seen that the results obtained by DIM-ORNET improve those obtained for the same problem in previous studies (ECSVM [13] and IM-ORNET [34]). Furthermore, the use of dynamic weights in the evolution improve the results in this dataset for both GMS and AMAE.…”

Section: Resultssupporting

confidence: 79%

“…In this case the fitness function is the one presented in Section 3.2, without considering the dynamic update of the costs (i.e. the method discussed in [34]).…”

Section: Evaluated Methodologiesmentioning

confidence: 99%

“…In this way, the algorithms hybridization follows a Darwinian principle [33]. The algorithm is based on the proposed in [34], where the main difference resides in the dynamic treatment of the class weights.…”

Section: Training Algorithm and Proposed Fitness Functionmentioning

confidence: 99%

“…Moreover, we must also consider the imbalance dataset problem, so we consider a dynamic cost (I M(C j )). These dynamic weights substitute the static weights proposed in [34], where the weights are fixed beforehand based on the number of patterns per class.…”

Section: Training Algorithm and Proposed Fitness Functionmentioning

confidence: 99%

See 3 more Smart Citations

Dynamically weighted evolutionary ordinal neural network for solving an imbalanced liver transplantation problem

Dorado-Moreno¹,

Prez-Ortiz

Gutirrez³

et al. 2017

Artificial Intelligence in Medicine

Self Cite

View full text Add to dashboard Cite

The combination of the proposed cost-sensitive evolutionary algorithm together with the application of an over-sampling technique improves the predictive capability of our model in a significant way (especially for minority classes), which can help the surgeons make more informed decisions about the most appropriate recipient for an specific donor organ, in order to maximize the probability of survival after the transplantation and therefore the fairness principle.

show abstract

Section: Resultssupporting

confidence: 79%

“…In this case the fitness function is the one presented in Section 3.2, without considering the dynamic update of the costs (i.e. the method discussed in [34]).…”

Section: Evaluated Methodologiesmentioning

confidence: 99%