Biopotential Signal Synchronization via Machine Learning Feature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biopotential signal synchronization methods struggle with accurately aligning signals from multiple capacitive sensors positioned at different locations on a subject, leading to desynchronization and noise in biometric data.
Innovation Solution
A method that involves receiving biopotential signals from multiple capacitive sensors, determining a delay between signals, and applying a time adjustment using identifiable features recognized by a machine learning process to synchronize further biopotential signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If biopotential signals are obtained by multiple capacitive sensors positioned at different locations on a subject, then the quantity and diversity of biometric data is improved, but signal synchronization accuracy deteriorates leading to desynchronization and noise
Solution Approach 1:
The patent applies preliminary action by using identifiable features from initial biopotential signals (first and second signals) to determine time delays and establish synchronization parameters before processing further biopotential signals. This pre-characterization using machine learning enables subsequent signals to be synchronized based on pre-determined delay values, preventing desynchronization issues.
Solution Approach 2:
The patent implements feedback by using identifiable features detected in biopotential signals to continuously adjust and determine time delays between signals from different capacitive sensors. The machine learning process analyzes signal features and provides feedback on delay adjustments, enabling dynamic synchronization that compensates for variations in signal transmission times across multiple sensors.
2Measurement precision
If time adjustment is applied to synchronize further biopotential signals using features from initial signals, then signal synchronization is improved, but processing complexity increases due to machine learning requirements
Solution Approach 1:
The patent reduces processing complexity by performing preliminary machine learning analysis on initial biopotential signals to extract identifiable features and determine synchronization parameters in advance. Once these parameters are established, subsequent signal synchronization can proceed using the pre-determined delay values without requiring continuous complex machine learning processing, thus reducing overall computational burden.
Solution Approach 2:
The patent applies copying by using the synchronization parameters and delay values derived from initial biopotential signals as templates for synchronizing subsequent further biopotential signals. Instead of performing full machine learning analysis on every signal, the system copies and applies the previously learned synchronization patterns, significantly reducing processing complexity while maintaining accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method, apparatus and computer program, the method comprising: receiving a first biopotential signal obtained by a first capacitive sensor; receiving a second biopotential signal obtained by a second capacitive sensor, the first capacitive sensor and the second capacitive sensor being positioned at different locations on a subject; synchronising biopotential signals obtained by the first capacitive sensor and the second capacitive sensor by applying a time adjustment to biopotential signals obtained by at least one of the first capacitive sensor or the second capacitive sensor; wherein features in at least one of the first biopotential signal and the second biopotential signal are used to synchronise the biopotential signals obtained by the first capacitive sensor and the second capacitive sensor.