Sleep Stage Classification Using Subject-Specific Spectral Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sleep stage classification methods rely on fixed spectral boundaries that are not individually adjusted for each subject, leading to inaccurate sleep stage determinations.
Innovation Solution
A system and method that use sensors and processors to generate and analyze respiratory wave amplitude metrics, transforming them into a frequency domain to determine individual and aggregated frequencies, and adjust spectral boundaries using linear regression based on aggregated frequencies to classify sleep stages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fixed spectral boundaries are used for sleep stage classification, then the classification method is simple and consistent, but the accuracy of sleep stage determination deteriorates due to lack of individual adjustment
Solution Approach 1:
The system performs preliminary action by determining individual spectral boundaries for each subject during an initial sleep session before actual classification. The processor calculates subject-specific spectral boundaries based on respiratory wave amplitude metrics from the initial session, storing them for subsequent use. This preliminary customization enables accurate individualized classification without requiring complex real-time adjustments during actual sleep monitoring.
Solution Approach 2:
The invention applies parameter changes by modifying spectral boundary parameters from fixed standard values to individualized values based on each subject's respiratory characteristics. The processor adjusts spectral boundary parameters (such as frequency thresholds and amplitude criteria) according to subject-specific data, transforming the classification system from using universal fixed parameters to personalized dynamic parameters that adapt to individual physiological variations.
2Measurement precision
If individualized spectral boundaries are determined for each subject, then the accuracy of sleep stage classification improves, but the processing time and computational complexity increase
Solution Approach 1:
The system performs preliminary action by determining individual spectral boundaries for each subject during an initial sleep session before actual classification. The processor calculates subject-specific spectral boundaries based on respiratory wave amplitude metrics from the initial session, storing them for subsequent use. This preliminary customization enables accurate individualized classification without requiring complex real-time adjustments during actual sleep monitoring.
Solution Approach 2:
The system applies self-service by automatically determining spectral boundaries using the subject's own respiratory wave data without requiring manual intervention or complex external calibration. The processor autonomously analyzes the subject's physiological signals, identifies characteristic patterns, and generates personalized spectral boundaries independently, reducing both processing time and computational burden.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure pertains to a system (10) configured to determine spectral boundaries (216, 218) for sleep stage classification in a subject (12). The spectral boundaries may be customized and used for sleep stage classification in an individual subject. Spectral boundaries determined by the system that are customized for the subject may facilitate sleep stage classification with higher accuracy relative to classifications made based on static, fixed spectral boundaries that are not unique to the subject. In some implementations, the system comprises one or more of a sensor (16), a processor (20), electronic storage (22), a user interface (24), and/or other components.