Karlik, BekirHayta, Sengul Bayrak2020-03-262020-03-262014978-84-15814-84-9https://hdl.handle.net/20.500.12395/306852nd International Work-Conference on Bioinformatics and Biomedical Engineering (IWBBIO) -- APR 07-09, 2014 -- Granada, SPAINThe aim of this study is to diagnose epileptic seizures by using different machine learning algorithms. For this purpose, the frequency components of the EEG are extracted by using the discrete wavelet transform (DWT) and parametric methods based on autoregressive (AR) model. Both these two feature extraction methods are applied to the input of machine learning classification algorithms such as Artificial Neural Networks (ANN), Naive Bayesian, k-Nearest Neighbor (k-NN), Support Vector Machines (SVM) and k-Means. The results show that k-NN, ANN and SVM were the most efficient method according to test processing of both DWT and AR as feature extraction for recognition of epileptic seizures in EEG.eninfo:eu-repo/semantics/closedAccessMachine learning algorithmsepilepsyelectroencephalogram (EEG)discrete wavelet transform (DWT)auto regressive modelConference Object112WOS:000346381500001N/A