# Embedded Deep Learning for Sleep Staging

## TL;DR

This paper explores the application of embedded deep learning architectures for sleep staging in resource-constrained wearable devices, aiming to improve sleep analysis in consumer healthcare.

## Contribution

It introduces two deep learning models optimized for low-power wearables and compares their performance with traditional hand-crafted algorithms.

## Key findings

- Deep learning models can be adapted for resource-limited sleep monitoring devices.
- Embedded DL architectures show promising accuracy for sleep staging.
- Comparison indicates potential advantages over traditional algorithms.

## Abstract

The rapidly-advancing technology of deep learning (DL) into the world of the Internet of Things (IoT) has not fully entered in the fields of m-Health yet. Among the main reasons are the high computational demands of DL algorithms and the inherent resource-limitation of wearable devices. In this paper, we present initial results for two deep learning architectures used to diagnose and analyze sleep patterns, and we compare them with a previously presented hand-crafted algorithm. The algorithms are designed to be reliable for consumer healthcare applications and to be integrated into low-power wearables with limited computational resources.