Epilepsy Diagnosis Using PSO based ANN
Küçük Resim Yok
Tarih
2013
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
ALIFE ROBOTICS CO, LTD
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Electroencephalogram (EEG) is used routinely for diagnosis of diseases occurring in the brain. It is a very useful clinical tool in classification of epileptic attacks and epilepsy diagnosis. In this paper, epilepsy diagnosis by evaluation of EEG records is presented. Artificial Neural Networks (ANN) is used as a classification technique. Particle Swarm Optimization (PSO) method, which doesn't require gradient calculation, derivative information and any solution of differential equations is preferred for ANN training. This training method is compared with back propagation algorithm, which is one of the traditional methods, and the results are interpreted. In case of using the PSO algorithm, the training and test classification accuracies are %99.67 and %100, respectively. PSO based neural network model (PSONN) has a better classification accuracy than back propagation neural network model (BPNN) for epilepsy diagnosis.
Açıklama
18th International Symposium on Artificial Life and Robotics (AROB) -- JAN 30-FEB 01, 2013 -- Daejeon, SOUTH KOREA
Anahtar Kelimeler
Artificial neural networks, back propagation algorithm, EEG, epilepsy diagnosis, particle swarm optimization
Kaynak
PROCEEDINGS OF THE EIGHTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS (AROB 18TH '13)
WoS Q Değeri
N/A
