Wearable Sleep Detection Using Movement Measures and Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wearable electronic devices face challenges in accurately detecting user activities and sleep stages due to their compact design and limited processing power, which hinders efficient data processing and power management.
Innovation Solution
A wearable electronic device that generates movement measures from sensor data, classifies user states (active/inactive, awake/asleep) using statistical features, and adjusts power consumption based on detected states, allowing for automatic detection of sleep periods and stages without explicit user input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex computations are performed to accurately detect user activities and sleep stages, then detection accuracy is improved, but power consumption increases and processing efficiency decreases due to limited processor capabilities in compact wearable devices
Solution Approach 1:
The patent segments the sleep detection process into multiple stages: initial sleep period detection using movement measures, followed by sleep stage classification. This segmentation allows the system to use computationally efficient methods for the primary detection task while reserving more intensive processing for subsequent stage classification, thereby reducing overall power consumption while maintaining detection accuracy.
Solution Approach 2:
The system performs partial computation by first detecting sleep periods using simplified movement measure analysis, then applying more comprehensive sleep stage classification only when needed. This partial action approach avoids the excessive power consumption of continuously running full sleep stage analysis, achieving accurate detection only when necessary.
2Measurement precision
If comprehensive sleep stage classification is performed, then detection accuracy is improved, but device complexity increases beyond the capabilities of compact wearable processors
Solution Approach 1:
The patent divides sleep detection into two distinct segments: sleep period detection using movement measures, and sleep stage classification. This segmentation enables the use of simpler algorithms for period detection, reducing processor complexity requirements, while still allowing for accurate sleep stage classification when needed.
Solution Approach 2:
The patent introduces movement measures as an intermediary representation that bridges raw sensor data and sleep stage classification. This intermediary layer simplifies the computational burden by pre-processing sensor data into condensed movement features, making subsequent sleep stage classification more tractable for wearable device processors.
3Use of energy by moving object
If user input is required to initiate sleep tracking, then power consumption is reduced by avoiding continuous monitoring, but ease of operation decreases and automatic detection capability is lost
Solution Approach 1:
The patent implements self-service by enabling the wearable device to automatically detect sleep periods and stages without requiring user initiation or input. The system autonomously processes sensor data, classifies sleep stages, and manages power consumption based on detected states, eliminating the need for user interaction while maintaining ease of operation.
Solution Approach 2:
The system performs preliminary action by continuously analyzing movement measures in the background to detect sleep periods automatically. This preliminary detection enables the device to proactively adjust power consumption and notify users of sleep events without requiring users to manually initiate tracking, thereby improving ease of operation while managing power efficiently.
Data Source
AI summary
Aspects of automatically detecting periods of sleep of a user of a wearable electronic device are discussed herein. For example, in one aspect, an embodiment may obtain a set of features for periods of time from motion data obtained from a set of one or more motion sensors in the wearable electronic device or data derived therefrom. The wearable electronic device may then classify the periods of time into one of a plurality of statuses of the user based on the set of features determined for the periods of time, where the statuses are indicative of relative degree of movement of the user. The wearable electronic device may also derive blocks of time each covering one or more of the periods of time during which the user is in one of a plurality of states, wherein the states include an awake state and an asleep state.