Classification of EEG recordings by using fast independent component analysis and artificial neural network

Since there is no definite decisive factor evaluated by the experts, visual analysis of EEG signals in time domain may be inadequate. Routine clinical diagnosis requests to analysis of EEG signals. Therefore, a number of automation and computer techniques have been used for this aim. In this study we aim at designing a MLPNN classifier based on the Fast ICA that accurately identifies whether the associated subject is normal or epileptic. By analyzing a data set consisting of 100 normal and 100 epileptic EEG time series, we have found that the MLPNN classifier based on the Fast ICA achieved and sensitivity rate of 98%, and specificity rate of 90.5%. The results demonstrate that the testing performance of the neural network diagnostic system is found to be satisfactory and we think that this system can be used in clinical studies. Since the time series analysis of EEG signals is unsatisfactory and requires specialist clinicians to evaluate, this application brings objectivity to the evaluation of EEG signals.