sEMG Signal Elevation for Accurate Muscle Onset Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing signal processing systems struggle with accurate onset and offset detection in surface Electromyography (sEMG) signals due to their chaotic nature and contamination with noise and interference, affecting applications in healthcare, prosthetics, robotics, and sports science.
Innovation Solution
A processor-implemented method involving preprocessing, signal elevation using Variational Mode Decomposition (VMD), and adaptive threshold-based segmentation to enhance sEMG signal processing, identifying Intrinsic Mode Functions (IMFs) with least noise and closest power match, and performing logical OR operations to generate a combined sEMG signal for precise onset and offset detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional signal processing methods are used on raw sEMG signals, then the processing is simple and fast, but the onset and offset detection accuracy is poor due to noise and chaotic nature of the signals
Solution Approach 1:
The patent applies segmentation by dividing the sEMG signal processing into distinct stages: preprocessing to obtain envelope signal, signal elevation to enhance relevant features, and segmentation to identify onset and offset regions. This multi-stage approach systematically improves detection accuracy while managing complexity through structured processing steps.
Solution Approach 2:
The patent employs preliminary action by performing preprocessing operations (DC offset removal, band-pass filtering, full-wave rectification, low-pass filtering) before the main detection task. These preliminary steps prepare the signal by removing noise and extracting the envelope, making subsequent onset/offset detection more accurate.
2Measurement precision
If signal elevation is performed using VMD and IMF selection, then the detection accuracy is improved, but the processing time and computational load increase
Solution Approach 1:
The patent applies parameter changes by transforming the sEMG signal through multiple processing stages that modify its characteristics: envelope extraction changes amplitude characteristics, VMD decomposition changes frequency-domain parameters, and IMF selection optimizes based on noise level and power spectrum match. These parameter transformations progressively enhance detection accuracy.
Solution Approach 2:
The patent uses VMD decomposition and IMF components as intermediaries between the raw sEMG signal and the final detection. The IMF functions as a mediator that separates signal components by frequency, allowing selective enhancement of relevant muscle activity frequencies while filtering out noise, thus improving accuracy without requiring direct manipulation of the complex raw signal.
3Reliability
If multiple processing stages are applied to sEMG signals, then the quality of sEMG data is enhanced, but the system complexity and difficulty of implementation increase
Solution Approach 1:
The patent segments the complex processing system into modular stages: preprocessing module, signal elevation module (with VMD and IMF selection), and segmentation module. Each module performs a specific function, making the overall complex system more manageable and implementable while maintaining high data quality through systematic processing at each stage.
Data Source
Figure 1A
Figure 1B
Figure 2A
AI summary
Accurate onset detection helps in fine-tuning training regimens. However, the chaotic nature of raw EMG signals, contaminated with noise and interference from various sources, often complicates the task of accurate onset/offset detection. For the same reason, existing signal processing systems struggle to perform the onset and offset detection effectively, which in turn affects end applications. Embodiments disclosed herein provide a method and system for signal elevation based muscle activity detection. The system performs the signal elevation to highlight and detect onset and offset regions in a signal being processed. Further, based on the determined onset and offset regions, a muscle potential activity of the subject is determined.