Learning sleep stages from radio signals

Abstract

A method for tracking a sleep stage of a subject takes as input a sequence of observations sensed over an observation time period. The sequence of observation values is processed to yield a corresponding sequence of encoded observations using a first artificial neural network (ANN) and the sequence of encoded observation values is processed to yield a sequence of sleep stage indicators using a second artificial network. Each observation may correspond to an interval of the observation period (e.g., at least 30 seconds). The first ANN may be configured to reduce information representing a source of the sequence of observations in the encoded observations.

Description

[0001] Cross References to Related Applications [0002] This application claims U.S. Provisional Application 62 / 476,815, filed March 26, 2017, entitled "Learning Sleep Stages from Radio Signals" and U.S. Provisional Application 62, filed June 12, 2017, entitled "Learning Sleep Stages from Radio Signals" / 518,053 priority, both of which are hereby incorporated by reference. This application is also related to US Patent Publication 2017 / 0042432, entitled "Vital Signs Monitoring Via Radio Reflections," and US Patent 9,753,131, entitled "Motion Tracking Via Body Radio Reflections," both of which are also incorporated herein by reference. Background technique [0003] The present invention relates to inferring the sleep stage of a subject via radio signals. [0004] Sleep plays a vital role in an individual's health and well-being. Sleep progresses in cycles involving multiple sleep stages: wakefulness, light sleep, deep sleep, and REM (rapid eye movement). Different stages are...

AI Technical Summary

Problems solved by technology

Accuracy is relatively low (about 64%), and the model does not generalize beyond the single environment where the measurements were collected

Images