REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wild

Rahul Duggal*, Scott Freitas*, Cao Xiao, Duen Horng (Polo) Chau, Jimeng Sun

This research is an effort to build noise robust and efficient neural nets for home sleep monitoring on edge devices.

Abstract

In recent years, significant attention has been devoted towards integrating deep learning technologies in the healthcare domain. However, to safely and practically deploy deep learning models for home health monitoring, two significant challenges must be addressed: the models should be (1) robust against noise; and (2) compact and energy-efficient. We propose REST, a new method that simultaneously tackles both issues via 1) adversarial training and controlling the Lipschitz constant of the neural network through spectral regularization while 2) enabling neural network compression through sparsity regularization. We demonstrate that REST produces highly-robust and efficient models that substantially outperform the original full-sized models in the presence of noise. For the sleep staging task over single-channel electroencephalogram (EEG), the REST model achieves a macro-F1 score of 0.67 vs. 0.39 achieved by a state-of-the-art model in the presence of Gaussian noise while obtaining 19x parameter reduction and 15x MFLOPS reduction on two large, real-world EEG datasets. By deploying these models to an Android application on a smartphone, we quantitatively observe that REST allows models to achieve up to 17x energy reduction and 9x faster inference. We open source the code repository with this paper: https://github.com/duggalrahul/REST.

Citation

REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wild
Rahul Duggal*, Scott Freitas*, Cao Xiao, Duen Horng (Polo) Chau, Jimeng Sun
The Web Conference (WWW). Taipei, Taiwan, 2020.
Project PDF Blog Video Code BibTeX * Authors contributed equally