ECG Signal Extraction Using Wavelet Transform for Baseline Drift Removal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Baseline drift in ECG signals hinders accurate visualization and computerized detection of waveforms, making it difficult to extract clinically relevant features without removing the drift.
Innovation Solution
The method involves performing time-frequency transformations using Continuous Wavelet Transform with Gabor mother wavelets, selecting pertinent scales, and estimating peak positions and amplitudes without baseline drift removal, allowing for accurate feature extraction and waveform similarity detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If baseline drift removal is applied to ECG signals, then waveform visualization and detection accuracy are improved, but signal processing complexity and potential loss of clinically relevant information increase
Solution Approach 1:
The patent extracts and removes only the specific baseline drift component from the ECG signal using wavelet transformation, rather than applying complex filtering that would remove entire frequency bands. The method identifies and separates the baseline drift as a distinct component that can be eliminated while preserving the clinically relevant ECG waveform information.
Solution Approach 2:
The patent changes the parameter representation of the ECG signal by transforming it into the wavelet domain, where baseline drift and ECG components can be distinguished by their different temporal and frequency characteristics. This parameter transformation allows selective processing of baseline drift without affecting the ECG signal integrity.
2Object-affected harmful factors
If filtering affected frequency bands is used to remove baseline drift, then baseline drift effects are reduced, but clinically relevant features in those frequency bands are also lost
Solution Approach 1:
The patent converts the harmful baseline drift into a beneficial diagnostic feature by preserving it in the processed signal. Instead of removing baseline drift completely, the method processes it in a way that maintains its presence while eliminating its interfering effects, allowing clinicians to potentially use baseline drift characteristics as additional diagnostic information.
Solution Approach 2:
The patent introduces wavelet transformation as an intermediary process that mediates between the baseline drift and the ECG signal. This intermediary transformation allows the baseline drift to be identified and handled separately, preventing it from interfering with ECG detection while preserving both components for potential clinical analysis.
3Shape
If traditional filtering methods are applied to remove baseline drift, then waveform visualization is improved, but independent detection of onsets and offsets becomes difficult
Solution Approach 1:
The patent segments the ECG signal into distinct components (baseline drift, ECG waves, noise) using wavelet transformation. This segmentation allows each component to be processed independently, with the baseline drift component handled separately from the ECG waveform components, thereby preserving the ability to accurately detect onsets and offsets of ECG waves.
Solution Approach 2:
The patent moves the signal analysis from the traditional time domain to the time-frequency domain using wavelet transformation. This dimensional change provides an additional frequency dimension that helps distinguish baseline drift from ECG components, enabling improved waveform visualization while maintaining accurate onset and offset detection capabilities.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate detection of ECG signal features without filtering affected frequency bands, preventing baseline drift effects and allowing independent detection of onsets and offsets, thus improving clinical feature extraction.
Implementation Method 1
performing a time-frequency transformation on the received electrocardiography signal to generate a corresponding scalogram
Data Source
AI summary
An electrocardiography signal extraction method is performed on a processor of a computer system and includes receiving an electrocardiography signal, performing a time-frequency transformation on the received electrocardiography signal to generate a corresponding scalogram, selecting a predetermined R-pertinent scale, performing the time-frequency transformation at the selected predetermined R-pertinent scale to generate a R-pertinent summarized response, obtaining a R peak position, selecting a predetermined QRS-pertinent scale, performing the time-frequency transformation at the selected predetermined QRS-pertinent scale, obtaining a Q peak position and a S peak position of the electrocardiography signal by finding relative maximum negative responses before and behind the R peak position respectively, obtaining a QRSon position and a QRSoff position by finding relative minimum second derivatives of the responses before the Q peak position and behind the S peak position, respectively.