Non-Contact Sleep Disorder Detection via Radar and Optical Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional polysomnography for diagnosing Non-Rapid Eye Movement (NREM) sleep behavior disorders is expensive, uncomfortable, and requires hospital-based testing with multiple contact sensors, limiting its convenience and effectiveness for screening.
Innovation Solution
A sleep management system comprising multiple sensors (pressure, UWB, radar, PPG, electrocardiogram, and acceleration sensors) that collect data, process it using machine learning models, and determine NREM sleep behavior disorders through a hub and user device, enabling convenient screening and alerting mechanisms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If polysomnography is performed in hospitals with contact sensors, then measurement precision for NREM sleep behavior disorder is improved, but ease of operation and user comfort deteriorate
Solution Approach 1:
The patent replaces contact-based mechanical sensors (polysomnography equipment) with non-contact sensors including radar sensors, optical sensors, and acoustic sensors. These sensors detect sleep behaviors through electromagnetic waves, light reflection, and sound waves without physical contact, thereby maintaining measurement precision while significantly improving ease of operation and user comfort.
Solution Approach 2:
The patent introduces a server as an intermediary that receives data from multiple non-contact sensors, processes the information using machine learning models, and generates diagnosis results. This intermediary system integrates data from radar, optical, and acoustic sensors to achieve accurate NREM sleep behavior disorder detection without requiring direct contact with the patient.
2Measurement precision
If polysomnography is performed in hospitals, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent divides the diagnostic system into separate functional modules: non-contact sensors for data collection, a server for data processing and machine learning model execution, and a user interface for result delivery. Each module performs a specific function, allowing the system to achieve high measurement precision through specialized components while reducing overall device complexity through modular design.
Solution Approach 2:
The patent employs multi-functional non-contact sensors that can detect multiple parameters simultaneously (movement, breathing patterns, heart rate) using the same sensor hardware. The server performs multiple functions including data aggregation, preprocessing, machine learning inference, and result generation, reducing the need for separate dedicated devices for each function.
3Measurement precision
If multiple contact sensors are used for polysomnography, then measurement precision is improved, but ease of operation deteriorates due to uncomfortable wear
Solution Approach 1:
The patent replaces all contact-based mechanical sensors with non-contact sensing technologies. Radar sensors detect movement and breathing patterns through electromagnetic wave reflection, optical sensors monitor physiological changes through light interaction, and acoustic sensors capture sound-based physiological signals. This substitution eliminates the need for wearable contact sensors, maintaining detection accuracy while dramatically improving user comfort and ease of operation.
Data Source
AI summary
Provided is a sleep management system, including a plurality of sensors including a first sensor and a second sensor being configured to collect data of a user, a hub device configured to receive first data collected by the first sensor and second data collected by the second sensor, obtain first processed data based on processing of the first data and second processed data based on processing of the second data, and a user device configured to receive the first processed data and the second processed data, obtain sleep state information corresponding to a sleep stage and a body movement of the user based on the first processed data and the second processed data, determine whether a non-rapid eye movement (NREM) sleep behavior disorder of the user occurs based on the user's sleep stage and the user's body movement, and perform a preset operation based on an occurrence of the NREM.