# Transfer Learning for Automatic Sleep Staging Using a Pre-Gelled Electrode Grid

## TL;DR

This paper presents a transfer learning approach to automatically stage sleep using a new sensor grid, achieving high accuracy with limited data.

## Contribution

The novel use of pre-training on large datasets and fine-tuning on small datasets enables sleep staging with a new sensor grid.

## Key findings

- An F1 score of 0.81 across all sleep phases was achieved using only EEG and EOG data from a new sensor grid.
- Pre-training on large PSG datasets followed by fine-tuning on small datasets improves performance for new sensor technologies.
- A method to approximate classical electrode positions using linear combinations of new sensor grid channels was explored.

## Abstract

Novel sensor solutions for sleep monitoring at home could alleviate bottlenecks in sleep medical care as well as enable selective or continuous observation over long periods of time and contribute to new insights in sleep medicine and beyond. Since especially in the latter case the sensor data differ strongly in signal, number and extent of sensors from the classical polysomnography (PSG) sensor technology, an automatic evaluation is essential for the application. However, the training of an automatic algorithm is complicated by the fact that the development phase of the new sensor technology, extensive comparative measurements with standardized reference systems, is often not possible and therefore only small datasets are available. In order to circumvent high system-specific training data requirements, we employ pre-training on large datasets with finetuning on small datasets of new sensor technology to enable automatic sleep phase detection for small test series. By pre-training on publicly available PSG datasets and finetuning on 12 nights recorded with new sensor technology based on a pre-gelled electrode grid to capture electroencephalography (EEG), electrooculography (EOG) and electromyography (EMG), an F1 score across all sleep phases of 0.81 is achieved (wake 0.84, N1 0.62, N2 0.81, N3 0.87, REM 0.88), using only EEG and EOG. The analysis additionally considers the spatial distribution of the channels and an approach to approximate classical electrode positions based on specific linear combinations of the new sensor grid channels.