文档介绍：Computer Methods and Programs in Biomedicine (2005) 78, 87—99
Classification of EEG signals using work
and logistic regression
Abdulhamit Subasi a, ∗, Ergun Erc¸elebi b
a Department of Electrical and Electronics Engineering, Kahramanmaras Sutcu Imam University,
46601 Kahramanmaras¸, Turkey
b Department of Electrical and Electronics Engineering, University of Gaziantep, 27310 Gaziantep, Turkey
Received 26 May 2004; received in revised form 12 October 2004; accepted 26 October 2004
KEYWORDS Summary Epileptic seizures are manifestations of epilepsy. Careful analyses of the
EEG; electroencephalograph (EEG) records can provide valuable insight and improved un-
Epileptic seizure; derstanding of the mechanisms causing epileptic disorders. The detection of epilep-
Lifting-based discrete tiform discharges in the EEG is an ponent in the diagnosis of epilepsy.
wavelet transform As EEG signals are non-stationary, the conventional method of frequency analysis
(LBDWT); is not highly essful in diagnostic classification. This paper deals with a novel
method of analysis of EEG signals using wavelet transform and classification using
Logistic regression (LR);
artificial work (ANN) and logistic regression (LR). Wavelet transform is
Multilayer perceptron
particularly effective for representing various aspects of non-stationary signals such
work as trends, discontinuities and repeated patterns where other signal processing ap-
(MLPNN) proaches fail or are not as effective. Through wavelet position of the EEG
records, transient features are accurately captured and localized in both time and
frequency context. In epileptic seizure classification we used lifting-based discrete
wavelet transform (LBDWT) as a preprocessing method to increase puta-
tional speed. The proposed algorithm reduces putational load of those al-
gorithms that were based on classical wavelet transform (CWT). In this study, we
introduce two fundamentally different approaches for