A time-scale based objective function for EEG signal parameters optimization

This paper concerns the optimization of EEG signal parameters for epileptic seizure detection. In a previous study, a macroscopic model has been used to model various waveforms of EEG signal and to optimize its parameters by means of a genetic algorithm (GA). In the GA-based method for EEG parameters estimation, an optimization procedure is used. The aim of the optimization procedure is to minimize an objective function. The minimized error function compares the desired waveform (real EEG signal) and the waveform of the signal provided by the model both in the time domain and frequency domain. In the present study, we propose a time-scale based representation for the objective function as an alternative to the time and frequency based objective function used in the early study. The proposed objective function takes into account the non-stationary nature of the EEG signal. The performance of the proposed wavelet-based objective function is compared to that of the spectral objective function.