Sleep Stage Classification Using Bidirectional LSTM in Wearable Multi-sensor Systems

TL;DR

This paper presents a novel approach using a low-cost wearable multi-sensor system combined with a bidirectional LSTM model to classify sleep stages accurately from cardiorespiratory signals, offering a practical alternative to traditional PSG tests.

Contribution

The study introduces a new wearable system and a deep learning model for sleep stage classification, achieving high accuracy and outperforming previous methods on large datasets.

Findings

Achieved 80.25% accuracy on a large public dataset.

Achieved 80.75% accuracy on 32 subjects from the authors' dataset.

Outperformed previous methods using small or large datasets.

Abstract

Understanding the sleep quality and architecture is essential to human being's health, which is usually represented using multiple sleep stages. A standard sleep stage determination requires Electroencephalography (EEG) signals during the expensive and labor-intensive Polysomnography (PSG) test. To overcome this inconvenience, cardiorespiratory signals are proposed for the same purpose because of the easy and comfortable acquisition by simplified devices. In this paper, we leverage our low-cost wearable multi-sensor system to acquire the cardiorespiratory signals from subjects. Three novel features are designed during the feature extraction. We then apply a Bi-directional Recurrent Neural Network architecture with Long Short-term Memory (BLSTM) to predict the four-class sleep stages. Our prediction accuracy is 80.25% on a large public dataset (417 subjects), and 80.75% on our 32 enrolled subjects, respectively. Our results outperform the previous works which either used small data sets and had the potential over-fitting issues, or used the conventional machine learning methods on large data sets.