Deep Muscle Signal Classification Using Surface EMG
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for measuring muscle activity, particularly deep muscle activity, using surface electromyography (EMG) are limited as they require multiple sensors and are not specific to deep muscles, making it difficult to accurately measure the activity of groups of muscles including both deep and surface muscles simultaneously.
Innovation Solution
A computer-implemented method that uses surface sensors to acquire and process electrical signals, extracting various temporal, frequency, time-frequency, fractal, and statistical variables to create a classifier that can differentiate the muscular activity of deep and surface muscles, allowing for the characterization of muscle groups with a limited number of sensors.
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 due to signal contamination from superficial muscles
Solution Approach 1:
The patent segments the muscle group into deep muscles and superficial muscles, and segments the signal processing into multiple stages: raw signal acquisition, artifact removal specific to superficial muscles, and extraction of deep muscle signals. This segmentation allows the system to handle the mixed signal from multiple muscle layers and isolate the deep muscle component.
Solution Approach 2:
The patent introduces an intermediary processing layer that models and removes superficial muscle artifacts before extracting deep muscle signals. This intermediary step acts as a mediator between the raw contaminated signal and the final deep muscle measurement, enabling accurate deep muscle detection despite signal contamination.
2Measurement precision
If multiple sensors are used to characterize individual muscles, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent makes a single sensor placement serve multiple functions: it simultaneously captures signals from both deep and superficial muscles, and the processed output provides information about deep muscle activity specifically. This multi-functionality eliminates the need for separate sensor placements for different muscle layers.
Solution Approach 2:
The patent transforms the signal parameters through processing: it changes from raw EMG signals containing mixed muscle information to processed signals with superficial muscle artifacts removed and deep muscle signals extracted. This parameter transformation enables precise deep muscle measurement without adding physical sensors.
3Device complexity
If a single sensor characterizes multiple surface muscles, then device complexity is reduced, but measurement precision deteriorates as information becomes combined and non-specific
Solution Approach 1:
The patent extracts the deep muscle signal component from the mixed signal captured by a single sensor. By removing superficial muscle artifacts and isolating the deep muscle contribution, the system achieves specific deep muscle measurement information that would otherwise be lost in the combined signal.
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 and individualized measurement of muscular activity in groups of muscles comprising both deep and surface muscles, improving accuracy and reducing the number of sensors needed, applicable across various anatomical areas for rehabilitation, sports, and diagnostics.
Implementation Method 1
measurement by electromyography (EMG) is known, consisting in positioning adhesive electrodes on the patient's skin
Data Source
Figure 1A~1B
Figure 2A~2C
Figure 3A~3B
AI summary
The present invention relates to a computer-implemented method for classifying physiological signals from the specific muscle 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 muscle 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 use of the measurement method for an application selected from among functional rehabilitation, muscle strengthening for wellness and/or aesthetic purposes, prevention and functional diagnosis, as well as to a computer program product.