[Abstract] Nowadays, among the Deep Learning works, there is a tendency to develop networks with millions of trainable parameters. However, this tendency has two main drawbacks: overfitting and resource consumption due to the low-quality features extracted by those networks. This paper presents a study focused on the scoring of sleeping EEG signals to measure if the increase of the pressure on the features due to a reduction of the number though different techniques results in a benefit. The work also studies the convenience of increasing the number of input signals in order to allow the network to extract better features. Additionally, it might be highlighted that the presented model achieves comparable results to the state-of-the-art with 1000 times less trainable and the presented model uses the whole dataset instead of the simplified versions in the published literature.

This work has been partially funded by the Carlos III Health Institute and the European Regional Development Funds (FEDER) [PI17/01826]. It was also partially supported by different grants and projects from the Xunta de Galicia [ED431D 2017/23; ED431D 2017/16; ED431G/01; ED431C 2018/49]

Xunta de Galicia; ED431D 2017/23

Xunta de Galicia; ED431D 2017/16

Xunta de Galicia; ED431C 2018/49

Xunta de Galicia; ED431G/01