Wakefulness determination method
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wakefulness determination methods inaccurately assess a driver's drowsiness due to simultaneous increases in respiration interval (RI) and Respiration root Mean Square Successive Difference (RrMSSD) during concentration or conversation, and are influenced by individual characteristics, leading to incorrect drowsiness determination.
Innovation Solution
A wakefulness determination method utilizing a respiration sensor to obtain respiratory data, a calculation unit to compute the degree of change in respiration, and a Bayesian filter to determine wakefulness by multiplying the probability of drowsiness likelihood with prior probabilities, adjusted based on operation signals and stored data, to reduce individual characteristic influences and increase accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If RI and RrMSSD are used as indicators for wakefulness determination, then momentary variations in RI can be accurately obtained and influence of vibration noises is reduced, but wrongful determination of drowsiness occurs when RI and RrMSSD simultaneously increase due to concentration or conversation
Solution Approach 1:
The patent changes the parameter used for wakefulness determination from simple RI and RrMSSD values to the degree of change in respiration (derivative of respiratory data). This parameter transformation allows accurate detection of drowsiness while avoiding false positives during concentration or conversation, as the rate of change in respiration differs from the absolute values during these states.
2Productivity
If fixed determination criteria based on RI and RrMSSD changes are used, then wakefulness determination can be performed, but individual characteristics cause difficulty in accurate determination across different persons
Solution Approach 1:
The patent introduces a learning mechanism that dynamically adjusts determination criteria based on individual characteristics. The system learns each person's unique respiration patterns over time and adapts the drowsiness determination thresholds accordingly, transforming the static determination process into a dynamic, personalized system that improves accuracy while maintaining efficiency.
Data Source
AI summary
The present disclosure provides a wakefulness determination method for accurately determining wakefulness. The wakefulness determination method uses a respiration sensor that obtains respiratory data about respiration of a seated occupant, a calculation unit that calculates the respiratory data obtained from the respiration sensor, and a controller including a determination unit that determines a state of the seated occupant. The wakefulness determination method includes: obtaining, by the respiration sensor, respiratory data of the seated occupant; calculating, by the calculation unit, a degree of change in respiration from the obtained respiratory data; and determining, by the determination unit, wakefulness of the seated occupant by using a Bayesian filter where a probability of occurrence of drowsiness in the seated occupant for the degree of change in respiration is taken as a likelihood and the likelihood is multiplied by a prior probability of occurrence of drowsiness.