Using Genetic Algorithms for Automatic Recurrent ANN Development: an Application to EEG Signal Classification

Rivero, Daniel; Aguiar-Pulido, Vanessa; Fernández-Blanco, Enrique; Gestal, M.

Use this link to cite:

http://hdl.handle.net/2183/20701

Using Genetic Algorithms for Automatic Recurrent ANN Development: an Application to EEG Signal Classification

Files

Rvero_Usng.pdf (259.91 KB)

Identifiers

URI: http://hdl.handle.net/2183/20701

Publication date

2013

Authors

Rivero, Daniel

Aguiar-Pulido, Vanessa

Fernández-Blanco, Enrique

Gestal, M.

Bibliographic citation

Rivero D, Aguiar-Pulido V, Fernández-Blanco E, Gestal M. Using genetic algorithms for automatic recurrent ANN development: an application to EEG signal classification. Int J Data Mining Modelling Management. 2013;5(2):182-191

Abstract

[Abstract] ANNs are one of the most successful learning systems. For this reason, many techniques have been published that allow the obtaining of feed-forward networks. However, fe w works describe techniques for developing recurrent networks. This work uses a genetic algorithm for automatic recurrent ANN devel opment. This system has been applied to solve a well-known problem: classi fication of EEG signals from epileptic patients. Results show the high performance of this system, and its ability to develop simple networks, with a low number of neurons and connections.