Signal Elevation for Accurate sEMG Muscle Activity 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 clinical analysis, prosthetics, robotics, and sports science.
Innovation Solution
A method and system that preprocesses raw sEMG signals to obtain an sEMG envelope, decomposes it into Intrinsic Mode Functions (IMFs), identifies a candidate IMF with minimal noise and closest power match, elevates the envelope using this IMF, and performs segmentation to determine onset and offset regions, generating a combined sEMGe signal representing muscle potential activity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If raw sEMG signals are used directly for onset and offset detection, then the detection process is simple, but the detection accuracy is low due to noise and interference
Solution Approach 1:
The patent segments the sEMG signal processing into distinct stages: preprocessing (DC offset removal, powerline noise removal, band-pass filtering, full wave rectification, low-pass filtering) to obtain envelope signal, signal elevation to obtain conditioned signal, and segmentation to determine onset and offset regions. This systematic segmentation addresses the contradiction by making the complex processing manageable while ensuring high detection accuracy at each stage.
Solution Approach 2:
The patent applies preliminary actions by performing preprocessing operations before the main detection task. Specifically, DC offset removal, powerline noise removal, band-pass filtering, full wave rectification, and low-pass filtering are performed in advance to obtain a clean envelope signal, which then undergoes signal elevation. These preliminary actions prepare the signal for accurate onset and offset detection without requiring complex real-time processing during detection.
2Measurement precision
If signal elevation is performed using traditional methods, then the processing is straightforward, but the onset and offset detection accuracy remains insufficient due to chaotic signal nature
Solution Approach 1:
The patent applies parameter changes by transforming the envelope signal through signal elevation, which modifies the signal parameters to enhance the visibility of onset and offset regions. The conditioned signal obtained after signal elevation has altered amplitude and temporal characteristics that make onset and offset detection more reliable, directly addressing the difficulty of detecting boundaries in chaotic sEMG signals.
Solution Approach 2:
The patent introduces an intermediary conditioned signal between the raw envelope signal and the final onset/offset detection. The signal elevation process creates this intermediate representation that bridges the gap between the noisy envelope signal and the clear onset/offset boundaries, making the detection task more feasible without requiring direct analysis of the chaotic original signal.
3Reliability
If noise removal is applied to clean the sEMG signals, then the signal quality improves, but the processing complexity and time increase
Solution Approach 1:
The patent performs noise removal as a preliminary action during the preprocessing stage, before the main detection task. DC offset removal, powerline noise removal, band-pass filtering, and low-pass filtering are applied in advance to obtain a clean envelope signal. This approach ensures high signal quality for subsequent detection while allowing the actual onset and offset detection to proceed efficiently without repeated noise filtering during the critical detection phase.
Solution Approach 2:
The patent segments noise removal operations into specific preprocessing steps (DC offset removal, powerline noise removal, band-pass filtering, low-pass filtering) that are performed once during signal preparation. This segmentation allows the system to invest time in comprehensive noise removal upfront, then perform rapid onset and offset detection on the already-cleaned signal, thereby balancing signal quality improvement with processing time efficiency.
Data Source
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.