ECoG signal classification based on nonlinear dynamics using GA-MLPNN
Xiaoping Chen · 2007
In order to classify electrocorticogram(ECoG) signals of different mental tasks in a brain-computer interface(BCI) system,a method based on the combination of genetic algorithm (GA) and multilayer perceptron neural network(MLPNN) was presented.The GA approach was used to opti mize ECoG channels selection,which mini mized the number of channels while maxi mizing the classification performance.Error back-propagation(EBP) algorithm was used as the learning mechanismof MLPNN.The nonlinear dynamics features(e.g.permutation entropy (PE) and Hurst exponent(HE)) were chosenfor the channel selection and classification because the two nonlinear parameters gave high calculation performance and great discri minative ability.The results showthat the average classification rate of 87 % was obtained using the 15 selected channels as opposed to only 79 %by using all 64 channels.