EOG-Based Sleep Staging Using Decision Tree Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional sleep staging methods using electrooculography (EOG) are time-consuming and prone to misjudgment, and heart rate-based methods suffer from low accuracy due to individual variability, necessitating a more precise and less intrusive approach for accurate sleep state determination.
Innovation Solution
An EOG-based sleep staging method utilizing a decision tree to analyze eye movement characteristics such as eye movement ratio, blink count, low-frequency power ratio, high-frequency power ratio, alpha ratio, spindle ratio, and mean amplitude of the EOG signal to determine sleep states like WAKE, REM, S1, S2, and SWS stages, with a non-transitory computer readable medium and electronic device for executing this method.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual scoring approach is used for sleep staging, then scoring accuracy can be maintained by expert judgment, but the process is time-consuming and liable to misjudge
Solution Approach 1:
The patent replaces the manual mechanical scoring process with an automated computer-based system that processes EOG signals through digital signal processing algorithms, frequency domain analysis, and automated decision-making logic to determine sleep stages, thereby eliminating time consumption while maintaining accuracy
Solution Approach 2:
The patent creates a computational model that replicates expert scoring behavior by analyzing EOG signal characteristics and applying rule-based decision logic to automatically classify sleep stages, producing results that copy the accuracy of manual expert scoring without the time penalty
2Ease of operation
If heart rate-based sleep staging method is used, then low-disturbance and easy recording are achieved, but scoring accuracy is affected due to individual variability
Solution Approach 1:
The patent changes the measurement parameter from heart rate to EOG signal characteristics, specifically analyzing frequency domain parameters (alpha ratio, beta ratio, delta ratio) and time-domain parameters (blink count, eye movement ratio) that are less susceptible to individual variability and provide more reliable sleep staging accuracy
Solution Approach 2:
The patent replaces heart rate measurement with EOG signal acquisition and processing, using digital signal processing to extract sleep stage information from ocular electrical signals, thereby improving accuracy while maintaining ease of recording
3Measurement precision
If multi-channel polysomnography recording is used, then comprehensive physiological signals are recorded for accurate sleep staging, but the testing approach causes disturbance to sleep quality
Solution Approach 1:
The patent extracts and utilizes only the EOG signal component from the multi-channel PSG system, focusing specifically on ocular electrical signals for sleep staging while eliminating the need for other invasive sensors and complex multi-channel recording, thereby reducing disturbance to sleep quality
Solution Approach 2:
The patent extracts the essential sleep staging information from EOG signals alone, separating the sleep staging function from comprehensive multi-channel monitoring, thereby achieving accurate sleep staging with minimal disturbance to the subject
Data Source
AI summary
This invention mainly discloses an EOG-based sleep staging method which is used to improve of an accuracy of automatic sleep judging result. The method may be executed by a processor and comprises steps of reading a to-be-test data having a variation depending on time of EOG generated by a user during a sleep process; acquiring a plurality of eye movement characteristics based on a variation of the EOG of a period, with the characteristics including an eye movement ratio, a blink count, a low frequency power ratio, a high frequency power ratio, an alpha rhythm ratio, a spindle rhythm ratio, a delta rhythm ratio and an average amplitude of eletrooculogram (EOG) signals; and determining a sleep state of the period is a “WAKE stage”, a “REM stage”, a “S1 stage”, a “S2 stage”, or a “SWS stage” based on the EOG characteristics. Furthermore, a computer readable medium with stored programs, and electronic apparatuses are provided.