Classifying Deep Muscle Activity via Surface EMG Signal Decomposition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for measuring muscular activity, particularly those using surface electromyography (EMG), struggle to accurately differentiate between the specific activity of deep and superficial muscles, often requiring multiple sensors and being limited to superficial muscle analysis.
Innovation Solution
A computer-implemented method that uses a limited number of surface sensors to classify physiological signals from muscle groups containing both deep and superficial muscles, involving signal preprocessing, feature extraction, and the creation of a classifier to differentiate muscle co-contraction patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If surface EMG electrodes are used to measure deep muscle activity, then measurement capability is extended to deep muscles, but measurement precision deteriorates with 6% to 12% error and inability to specifically characterize individual deep muscles
Solution Approach 1:
The method segments the mixed EMG signal into contributions from individual muscles (both superficial and deep) by treating each muscle as a separate source. This segmentation allows the system to distinguish and quantify the activity of each muscle independently, resolving the precision problem while maintaining the ability to measure multiple muscles with limited electrodes.
Solution Approach 2:
The invention introduces a mathematical decomposition dimension by representing the EMG signal as a linear combination of muscle activation patterns. This transforms the problem from spatial measurement (electrode position) to a signal space decomposition, enabling precise characterization of individual muscle activity through algorithms rather than requiring separate physical sensors for each muscle.
2Measurement precision
If multiple sensors are used to characterize multiple muscles, then measurement precision improves, but device complexity increases with more sensors required than muscles to be characterized
Solution Approach 1:
Each EMG electrode in the system is designed to be multi-functional, capturing signals from multiple underlying muscles simultaneously. Rather than requiring one electrode per muscle, the same electrode serves multiple measurement purposes by detecting the composite signal, which is then decomposed computationally to extract individual muscle contributions.
Solution Approach 2:
The invention changes the measurement parameters from direct spatial mapping (electrode-to-muscle correspondence) to signal space parameters (activation patterns and weights). By transforming the problem into identifying the weights of muscle activation patterns in the composite signal, the system achieves precise muscle characterization with fewer physical sensors.
3Ease of operation
If surface EMG is used for superficial muscles according to SENIAM recommendations, then ease of operation is maintained, but adaptability is limited to only superficial muscles and cannot measure deep muscle activity
Solution Approach 1:
The system performs preliminary action by pre-defining and storing the EMG signal patterns characteristic of each muscle in the anatomical region. These reference patterns are established beforehand, allowing the real-time measurement system to quickly compare incoming signals against known patterns and identify which muscles are active, thereby extending adaptability without complicating the measurement procedure.
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
Enables the specific measurement of muscular activity in muscle groups with both deep and superficial muscles using fewer sensors than the number of muscles to be characterized, improving accuracy and applicability across various anatomical regions.
Implementation Method 1
electromyography (EMG), which involves positioning adhesive electrodes on the patient's skin strategically in relation to the anatomy of the muscle for which muscular activity is to be recorded
Data Source
AI summary
The present invention relates to a computer-implemented method for classifying physiological signals arising from the specific muscular activity of a muscle group comprising at least one deep muscle and at least one superficial muscle of a subject. The present invention also relates to a method for measuring the specific muscular activity of a muscle group comprising at least one deep muscle and at least one superficial muscle of a subject. The present invention further relates to the measuring method being used for an application chosen from among functional rehabilitation, muscle strengthening for wellbeing and/or aesthetic reasons, prevention and functional diagnosis, as well as to a computer program product.