Cascading Buffer Biometric Analysis for Real-Time State Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Real-time biometric feedback systems, such as those using EEG and ECG, face challenges in processing data quickly enough due to the need for long-duration analytics in the frequency domain, while also requiring fast feedback times and detecting biologically relevant voltage deflections, which is difficult with systems having low memory and computational power.
Innovation Solution
A cascading buffering system is implemented, where measures of central tendency or variability are saved in shorter and longer-term buffers, allowing for efficient detection of state shifts and events without the need for continuous data storage across long timescales, and dynamic adjustment to baseline shifts, reducing false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If long-duration analytics are performed in the frequency domain to accurately analyze biometric data, then measurement precision is improved, but processing time increases and real-time feedback capability deteriorates
Solution Approach 1:
The patent segments the continuous biometric data stream into multiple buffers with different durations (e.g., short-term buffer for immediate feedback, long-term buffer for baseline comparison). This allows the system to perform frequency domain analysis on manageable data segments while maintaining real-time feedback capability through the shorter buffers and using longer buffers only for reference comparisons.
2Measurement precision
If continuous data storage across long timescales is performed to detect state shifts, then measurement precision is improved, but memory requirements and computational load increase
Solution Approach 1:
The patent divides the long-term data storage requirement into multiple segmented buffers of different sizes and durations. Instead of storing all historical data continuously, the system maintains a hierarchy of buffers (short-term, medium-term, long-term) where each buffer stores data for a specific period. This segmentation reduces the immediate memory footprint while preserving the ability to detect state shifts by comparing across these segmented time windows.
Solution Approach 2:
The patent extracts and stores only the essential features (measures of central tendency or variability) from the raw biometric data at each time scale, rather than storing the complete raw data streams. This extraction approach significantly reduces memory requirements while preserving the information needed for state shift detection and baseline comparison.
3Device complexity
If fixed calibration periods are used to establish baselines, then device complexity is reduced, but adaptability to baseline shifts deteriorates and false positives increase
Solution Approach 1:
The patent transitions from static fixed calibration periods to dynamic adaptive baseline estimation using multiple time-scale buffers. The system continuously updates baseline estimates by comparing current data against historical data in the long-term buffer, allowing the baseline to adapt dynamically to physiological changes and baseline shifts. This dynamic approach increases complexity slightly but significantly improves adaptability and reduces false positives.
Solution Approach 2:
The patent implements a feedback mechanism where the system continuously monitors biometric data, compares it against adaptive baselines derived from historical data, and updates the baselines in response to detected state shifts. This feedback loop allows the system to automatically adapt to changing physiological conditions without requiring manual recalibration, improving adaptability while maintaining reasonable system complexity.
Data Source
AI summary
A system and method for identifying changes in a state or activity is described. A real-time event monitoring application, implemented in a hardware processor, computes features over varying sampling periods, which are stored in cascading buffers. The various sampling periods enable determination of trends of a computed feature, comparison of the trends of the computed feature with trends of other features, normalization of the computed feature based on the same or different features at the same or different time scales, scaling of the normalized computed feature relative to other features at the same or different time scale, and identification of a change in state or activity based on a scaled normalized computed feature.