A Closed-loop Sleep Modulation System with FPGA-Accelerated Deep Learning

TL;DR

This paper presents a portable, FPGA-accelerated deep learning system for real-time sleep stage classification and closed-loop sleep modulation, overcoming traditional limitations of wired setups and limited algorithm performance.

Contribution

It introduces a lightweight, FPGA-accelerated deep learning model for sleep staging that operates on a portable device, enabling real-time closed-loop sleep modulation.

Findings

Achieved 85.8% classification accuracy on a public sleep database.

Demonstrated closed-loop auditory stimulation in a test setup.

Validated model's generalization to different channels and data lengths.

Abstract

Closed-loop sleep modulation is an emerging research paradigm to treat sleep disorders and enhance sleep benefits. However, two major barriers hinder the widespread application of this research paradigm. First, subjects often need to be wire-connected to rack-mount instrumentation for data acquisition, which negatively affects sleep quality. Second, conventional real-time sleep stage classification algorithms give limited performance. In this work, we conquer these two limitations by developing a sleep modulation system that supports closed-loop operations on the device. Sleep stage classification is performed using a lightweight deep learning (DL) model accelerated by a low-power field-programmable gate array (FPGA) device. The DL model uses a single channel electroencephalogram (EEG) as input. Two convolutional neural networks (CNNs) are used to capture general and detailed features, and a bidirectional long-short-term memory (LSTM) network is used to capture time-variant sequence features. An 8-bit quantization is used to reduce the computational cost without compromising performance. The DL model has been validated using a public sleep database containing 81 subjects, achieving a state-of-the-art classification accuracy of 85.8% and a F1-score of 79%. The developed model has also shown the potential to be generalized to different channels and input data lengths. Closed-loop in-phase auditory stimulation has been demonstrated on the test bench.