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 parame...
详细信息
ISBN:
(纸本)9781467366748
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.
This paper proposes a new kernel method for online identification of nonlinear system. The proposed Support Vector Regression-Regularized Network (SVR-RN) method uses the technique SVR in an offline phase to reduce th...
详细信息
ISBN:
(纸本)9781467363020
This paper proposes a new kernel method for online identification of nonlinear system. The proposed Support Vector Regression-Regularized Network (SVR-RN) method uses the technique SVR in an offline phase to reduce the parameters number of the RKHS. Then the RN method is used to update theses reduced parameters.
A hybrid method based on Differential Evolution and Neural Network training algorithms is presented in this paper for improving the performance of neural network in the non linear system identification. For this purpo...
详细信息
ISBN:
(纸本)9781467363020
A hybrid method based on Differential Evolution and Neural Network training algorithms is presented in this paper for improving the performance of neural network in the non linear system identification. For this purpose, the local optimization algorithm of conjugate gradients (CG) is combined with the differential evolution algorithm (DE), which is a population-based stochastic global search method, to yield a computationally efficient algorithm for training multilayer perceptron networks for nonlinear system identification. After, a series of simulation studies of our method on the different nonlinear systems it has been confirmed that the proposed CG+DE algorithm has yielded better identification results in terms of time of convergence and less identification error.
In this paper, we have tried to tune PD Controller inverted pendulum using Multiobjective Differential Evolution by nonlinear equations. The objective was to apply the differential evolution algorithm in the aim of tu...
详细信息
In this paper, we have tried to tune PD Controller inverted pendulum using Multiobjective Differential Evolution by nonlinear equations. The objective was to apply the differential evolution algorithm in the aim of tuning the optimum solution of the PD controllers K p and K d by minimizing the Multiobjective function. The results of this simulation have been mentioned in the conclusion. It seems that the results be acceptable results.
In this paper we go about the segmentation and analysis of an electrocardiographic (ECG) signal. Firstly, it consists in working out the locations of different characteristic waves of this signal: the QRS complex and ...
详细信息
暂无评论