Non-contact Sleep Monitoring Using Radar Point Clouds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sleep monitoring solutions for elderly individuals are often intrusive, lack accuracy, and cannot effectively track sleep patterns, wake periods, and turning patterns in real-time, especially in non-clinical settings, which is crucial for early detection of sleep disorders that can lead to serious health issues.
Innovation Solution
A non-contact system using ultra-wideband radar and machine learning to detect point clouds representing user movements, classify sleep and wake states, and determine sleeping positions and patterns, providing continuous monitoring and alerting for deviations from normal patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of moving object
If wearable devices and bed pads are used for sleep monitoring, then sleep data can be collected continuously, but the monitoring becomes intrusive and requires permanent maintenance
Solution Approach 1:
The patent replaces mechanical contact-based monitoring (wearable devices, bed pads) with radar-based non-contact monitoring. The radar system uses electromagnetic waves to detect sleep parameters without physical contact, eliminating the need for wearables or bed inserts while maintaining continuous monitoring capability
Solution Approach 2:
The patent introduces radar technology as an intermediary between the monitoring system and the user. Instead of direct contact sensors, the radar system uses reflected electromagnetic waves to indirectly measure sleep parameters, providing continuous monitoring without intrusive physical presence
2Measurement precision
If polysomnography equipment is used in sleep centers, then diagnostic accuracy is high, but the system is complex and invasive and cannot be used for long-term tracking
Solution Approach 1:
The patent extracts the essential monitoring function from complex polysomnography systems by using radar to specifically detect chest and abdominal movements. This isolates the key sleep parameter detection (breathing patterns, sleep stages) from the full suite of invasive clinical equipment, achieving adequate accuracy with simpler technology
Solution Approach 2:
The patent replaces complex mechanical and electrical sensor systems with radar-based electromagnetic detection. The radar system uses signal processing of reflected waves to infer sleep parameters, substituting invasive electrical sensors and mechanical transducers with non-contact electromagnetic measurement
3Quantity of substance
If current sleep monitoring devices are used, then some sleep data can be collected, but accuracy in tracking sleep patterns and positions is insufficient
Solution Approach 1:
The patent employs dynamic analysis of radar point cloud data to track changes in sleep positions and patterns over time. By continuously analyzing the movement and position of detected points in three-dimensional space, the system can identify transitions between sleep stages and positions with high temporal resolution
Solution Approach 2:
The patent transitions from traditional one-dimensional or two-dimensional sleep monitoring to three-dimensional spatial tracking using radar point clouds. This adds dimensional information about sleep position and body orientation, enabling more accurate classification of sleep patterns and detecting subtle movements that indicate sleep disorders
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
Enables accurate, non-invasive, and continuous tracking of sleep patterns and positions, allowing for early detection of sleep disorders and potential health issues, improving the monitoring of elderly individuals in home or care facility settings.
Implementation Method 1
A non-contact system using ultra-wideband radar and machine learning to detect point clouds representing user movements
Data Source
AI summary
Determining sleep patterns of a user includes detecting a plurality of point clouds, each corresponding to a different position of the user at different times, forming a plurality of bounding boxes, each corresponding to coordinates of captured points of one of the point clouds, creating a wake/sleep classifier based on features of the point clouds, determining sleep positions of the user as a function of time based on the bounding boxes, and determining sleep patterns of the user based on the sleep positions of the user and on results of the sleep/wake classifier. Detecting a plurality of point clouds may include using a tracking device to capture movements of the user. The features of the point clouds may include intermediate data that is determined using scalar velocities of points in the point clouds, absolute velocities of points in the point clouds, and/or counts of points in the point clouds.