| dc.contributor.author |
Ferentinos, KP |
en |
| dc.date.accessioned |
2014-06-06T06:46:26Z |
|
| dc.date.available |
2014-06-06T06:46:26Z |
|
| dc.date.issued |
2005 |
en |
| dc.identifier.issn |
08936080 |
en |
| dc.identifier.uri |
http://dx.doi.org/10.1016/j.neunet.2005.03.010 |
en |
| dc.identifier.uri |
http://62.217.125.90/xmlui/handle/123456789/3010 |
|
| dc.subject |
Automatic neural network design |
en |
| dc.subject |
Biological engineering |
en |
| dc.subject |
Genetic algorithms |
en |
| dc.subject |
Neural networks |
en |
| dc.subject |
Training parameterization |
en |
| dc.subject.other |
Backpropagation |
en |
| dc.subject.other |
Error analysis |
en |
| dc.subject.other |
Feedforward neural networks |
en |
| dc.subject.other |
Genes |
en |
| dc.subject.other |
Genetic algorithms |
en |
| dc.subject.other |
Mathematical models |
en |
| dc.subject.other |
Topology |
en |
| dc.subject.other |
Automatic neural network design |
en |
| dc.subject.other |
Backpropagation algorithm |
en |
| dc.subject.other |
Biological engineering |
en |
| dc.subject.other |
Training parameterization |
en |
| dc.subject.other |
Biomedical engineering |
en |
| dc.subject.other |
algorithm |
en |
| dc.subject.other |
article |
en |
| dc.subject.other |
artificial neural network |
en |
| dc.subject.other |
genetic algorithm |
en |
| dc.subject.other |
genetic code |
en |
| dc.subject.other |
mathematical model |
en |
| dc.subject.other |
positive feedback |
en |
| dc.subject.other |
priority journal |
en |
| dc.subject.other |
task performance |
en |
| dc.subject.other |
Algorithms |
en |
| dc.subject.other |
Animals |
en |
| dc.subject.other |
Artificial Intelligence |
en |
| dc.subject.other |
Humans |
en |
| dc.subject.other |
Hydroponics |
en |
| dc.subject.other |
Neural Networks (Computer) |
en |
| dc.subject.other |
Predictive Value of Tests |
en |
| dc.subject.other |
Reproducibility of Results |
en |
| dc.title |
Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms |
en |
| heal.type |
journalArticle |
en |
| heal.identifier.primary |
10.1016/j.neunet.2005.03.010 |
en |
| heal.publicationDate |
2005 |
en |
| heal.abstract |
Two neural network (NN) applications in the field of biological engineering are developed, designed and parameterized by an evolutionary method based on the evolutionary process of genetic algorithms. The developed systems are a fault detection NN model and a predictive modeling NN system. An indirect or 'weak specification' representation was used for the encoding of NN topologies and training parameters into genes of the genetic algorithm (GA). Some a priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to some reasonable degree. Both one-hidden-layer and two-hidden-layer network architectures were explored by the GA. Except for the network architecture, each gene of the GA also encoded the type of activation functions in both hidden and output nodes of the NN and the type of minimization algorithm that was used by the backpropagation algorithm for the training of the NN. Both models achieved satisfactory performance, while the GA system proved to be a powerful tool that can successfully replace the problematic trial-and-error approach that is usually used for these tasks. © 2005 Elsevier Ltd. All rights reserved. |
en |
| heal.journalName |
Neural Networks |
en |
| dc.identifier.issue |
7 |
en |
| dc.identifier.volume |
18 |
en |
| dc.identifier.doi |
10.1016/j.neunet.2005.03.010 |
en |
| dc.identifier.spage |
934 |
en |
| dc.identifier.epage |
950 |
en |