Spectral Analysis of Pulse Rate and Motion for Sleep Stage Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining an individual's sleep stage are inaccurate and require costly or cumbersome equipment, failing to provide reliable measurements of sleep quality and physiological parameters.
Innovation Solution
A computer-implemented system using spectral analysis of pulse rate and motion data from sensors, such as photoplethysmographic (PPG) and accelerometer signals, to probabilistically estimate sleep stages by generating signal features and applying a sleep stage classifier.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional measurement systems and techniques are used to determine sleep stage, then equipment complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent replaces conventional mechanical/electrode-based sleep monitoring systems with an optical-based system using photoplethysmographic (PPG) sensors and accelerometers. This substitution enables accurate sleep stage detection through spectral analysis of pulse rate and motion data, achieving measurement precision comparable to or exceeding conventional methods while reducing device complexity and improving user comfort
Solution Approach 2:
The patent transforms the approach to sleep stage determination by changing the measured parameters from traditional EEG-based electrical signals to optical pulse rate and motion parameters. By applying spectral analysis to these alternative parameters, the system achieves accurate sleep stage classification without requiring complex electrode-based equipment
2Reliability
If conventional measurement systems are used, then device complexity is minimized, but reliability of sleep quality measurements deteriorates
Solution Approach 1:
The patent replaces conventional sleep monitoring equipment with wearable optical sensors that measure pulse rate and motion. This substitution improves reliability by capturing physiological parameters that directly reflect sleep stages, while simultaneously reducing equipment complexity to a wearable form factor that users can comfortably wear throughout the night
3Measurement precision
If spectral analysis of pulse rate and motion data is used, then measurement precision improves, but computational complexity increases
Solution Approach 1:
The patent extracts and focuses on specific spectral features from pulse rate and motion data that are most indicative of sleep stages. By identifying and analyzing only the most relevant frequency components rather than processing the entire signal spectrum, the system achieves high measurement precision while reducing computational complexity through selective feature extraction
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Provides more accurate sleep stage measurements without additional equipment, identifying abnormal sleep behaviors and physiological conditions like Insomnia and REM Behavior Disorder, improving sleep stage determination accuracy.
Implementation Method 1
receiving a photoplethysmographic (PPG) signal from a sensor
Data Source
AI summary
The present disclosure relates to systems and methods for probabilistically estimating an individual's sleep stage based on spectral analyses of pulse rate and motion data. In one implementation, the method may include receiving signals from sensors worn by the individual, the signals including a photoplethysmographic (PPG) signal and an accelerometer signal; dividing the PPG signal into segments; determining a beat interval associated with each segment; resampling the set of beat intervals to generate an interval signal; and generating signal features based on the interval signal and the accelerometer signal, including a spectrogram of the interval signal. The method may further include determining a sleep stage for the individual by comparing the signal features to a sleep stage classifier included in a learning library. The sleep stage classifier may include one or more functions defining a likelihood that the individual is in the sleep stage based on the signal features.