Wearable EMG Gesture Identification via Digit String Permutation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wearable electromyography (EMG) devices struggle to accurately and reliably identify gestures across different users and varying use conditions, requiring elaborate training procedures and failing to adapt to changes in device position, orientation, and skin conditions.
Innovation Solution
A wearable EMG device with EMG sensors and a processor that detects muscle activity, generates a permutation of a digit string based on signal rankings, and identifies gestures using a look-up table, eliminating the need for extensive user training by calibrating orientation through a reference gesture.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If elaborate training procedures are used to calibrate the wearable EMG device for each user and use condition, then gesture identification accuracy for specific users and conditions improves, but device complexity and time required for setup increase significantly
Solution Approach 1:
The system performs preliminary calibration using a reference gesture that establishes the relationship between sensor signals and gesture orientations before actual use. This preliminary action creates a lookup table with pre-computed signal patterns for different gestures, eliminating the need for elaborate real-time training procedures while maintaining high gesture identification accuracy across different users and conditions
2Measurement precision
If the wearable EMG device is calibrated for a specific user and position, then gesture identification accuracy improves for that specific configuration, but adaptability to different users, positions, and orientations deteriorates
Solution Approach 1:
The system achieves universality by creating a comprehensive lookup table that stores signal patterns for multiple gestures across different orientations and positions. The reference gesture calibration process captures the device's response to various gestures in different configurations, allowing the same calibrated system to accurately identify gestures from any user in any position without requiring re-calibration, thus simultaneously achieving both precision and adaptability
3Measurement precision
If multiple training trials are performed for each training gesture to improve calibration quality, then gesture identification accuracy improves, but the time required for setup and device complexity increase
Solution Approach 1:
The system performs the calibration action once during device setup using a reference gesture, and stores the resulting signal patterns in a lookup table for future use. This preliminary calibration captures the essential gesture characteristics without requiring repeated training trials during actual use, significantly reducing setup time while maintaining high gesture identification accuracy through the pre-computed reference data
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
The solution provides robust and accurate gesture identification for generic users and conditions without requiring elaborate training, improving user experience by adapting to changes in device position and orientation.
Implementation Method 1
Electromyography ('EMG') is a process for detecting and processing the electrical signals generated by muscle activity. EMG devices employ EMG sensors that are responsive to the range of electrical potentials (typically μV−mV) involved in muscle activity.
Data Source
AI summary
Systems, articles, and methods for performing gesture identification with improved robustness against variations in use parameters and without requiring a user to undergo an extensive training procedure are described. A wearable electromyography (“EMG”) device includes multiple EMG sensors, an on-board processor, and a non-transitory processor-readable storage medium that stores data and/or processor-executable instructions for performing gesture identification. The wearable EMG device detects, determines, and ranks features in the signal data provided by the EMG sensors and generates a digit string based on the ranked features. The permutation of the digit string is indicative of the gesture performed by the user, which is identified by testing the permutation of the digit string against multiple sets of defined permutation conditions. A single reference gesture may be performed by the user to (re-)calibrate the wearable EMG device before and/or during use.