Ensemble of convolution neural networks on heterogeneous signals for sleep stage scoring

Abstract Over the years, several approaches have tried to tackle the problem of performing an automatic scoring of the sleeping stages. Although any polysomnography usually collects over a dozen of different signals, this particular problem has been mainly tackled by using only the Electroencephalograms presented in these records. On the other hand, other recorded signals have been mainly ignored by most works. This paper explores and compares the advantage of using additional signals apart from Electroencephalograms. More specifically, this work uses the SHHS-1 dataset with 5,804 patients containing an electromyogram recorded simultaneously as two Electroencephalograms. To compare the results, first, the same architecture has been evaluated with different input signals and all possible combinations. These tests show how, using multiple signals especially if they are from different sources, improves the results of the classification. Additionally, the best models obtained for each combination of one or more signals have been used in ensemble models and, their performance has been compared showing the convenience of using these multi-signal models to improve the classification. The best overall model, an ensemble of Depth-wise Separable Convolutional Neural Networks, has achieved an accuracy of 86.06% with a Cohen’s Kappa of 0.80 and a $$F_{1}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mi>F</mml:mi> <mml:mn>1</mml:mn> </mml:msub> </mml:math> of 0.77. Up to date, those are the best results on the complete dataset and it shows a significant improvement in the precision and recall for the most uncommon class in the dataset.