Bio-information Estimation Using Probability Distribution Functions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating bio-information from ballistocardiogram (BCG) signals lack accuracy and efficiency, particularly in compact wearable devices, due to challenges in detecting characteristic points amidst noise and variability among users.
Innovation Solution
An apparatus and method that utilize a processor to detect characteristic points from BCG signals using a pre-defined probability distribution function, combining them with other bio-signals like ECG and PPG, to estimate bio-information such as blood pressure and vascular age, and generate personalized distribution functions based on user data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If characteristic points are detected from BCG signals using conventional methods, then the device can estimate bio-information, but the accuracy is reduced due to noise and variability among users
Solution Approach 1:
The patent applies preliminary action by pre-defining probability distribution functions based on time intervals between characteristic points in BCG signals from multiple users before actual measurement. This pre-processing creates a reference framework that guides subsequent characteristic point detection, reducing the impact of noise and inter-user variability during real-time estimation of bio-information.
2Reliability
If multiple sensors and processing steps are used to improve accuracy, then bio-information estimation reliability increases, but device complexity increases
Solution Approach 1:
The patent implements universality by using a single BCG signal for multiple bio-information estimation purposes. The probability distribution function framework is designed to be universal across different users and applications, allowing the same signal processing approach to estimate various cardiovascular parameters without requiring separate specialized systems for each measurement type.
3Measurement precision
If personalized probability distribution functions are generated for each user, then estimation accuracy improves, but processing time and computational load increase
Solution Approach 1:
The patent applies preliminary action by pre-generating probability distribution functions during a calibration phase using BCG signals collected from multiple users. These pre-computed functions are stored and later applied during actual bio-information estimation, avoiding the need to perform complex computations in real-time and thus reducing measurement time while maintaining personalized accuracy.
Data Source
AI summary
An apparatus for estimating bio-information of a user may include a first sensor configured to measure a first signal from the user; a second sensor configured to measure a second signal from the user; and a processor configured to obtain a first characteristic point from the first signal; obtain a second characteristic point from the second signal based on the first characteristic point and a pre-defined probability distribution function; and estimate the bio-information of the user based on the second characteristic point.