GACNN SleepTuneNet: a genetic algorithm designing the convolutional neural network architecture for optimal classification of sleep stages from a single EEG channel

Abstract

This study presents a method for designing–by a genetic algorithm, without manual intervention–the featurelearning architecture for classification of sleep stages from a single EEG channel, when using a convolutional neuralnetwork called GACNN SleepTuneNet. Two EEG electrode positions were selected, namely FP2-F4 and FPz-Cz, fromtwo available datasets. Twenty-five generations were involved in diagnosis without hand-crafted features, to learn thearchitecture for classification of sleep stages based on AASM standard. Based on the results, our model not only achievedthe highest classification accuracy, but it also distinguished the sleep stages based on either of the two EEG electrodesignals, in both datasets. The results show that our model performed the best with highest overall accuracy rates andkappa statistic (CAP sleep: 95.61% and 0.94; Sleep EDF: 92.51% and 0.90) among other state-of-the-art methods thatrequire no manual intervention. Our model could automatically learn the features for classification of sleep stages, fordifferent raw EEG electrode positions in different datasets, without user-assisted feature extraction.