Wearable EMG Authentication Using Wet Electrodes and Digital Filtering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing EMG-based personal authentication systems are inconvenient due to their large size and limited functionality, and are vulnerable to bio-signal exploits, leading to security concerns as they can be hacked or copied.

Innovation Solution

An EMG signal-based user authentication apparatus and method that uses a wet-type electrode with a hydrogel component, a pre-processor to remove partial signals via digital filtering, and a controller to authenticate users by comparing derived parameters with pre-stored values using a combination of Artificial Neural Networks (ANN) and Support Vector Machines (SVM) for classification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If EMG-based personal authentication system is implemented, then user authentication functionality is provided, but the device size becomes large and convenience decreases

Engineering Contradiction:

Improveauthentication functionalityVSAvoidconvenience

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The EMG signal processing apparatus is integrated into a wearable device that can perform multiple functions including not only personal authentication but also gesture recognition and health monitoring, making the device more versatile and justifying its presence as a multi-functional wearable rather than a dedicated authentication device

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Speed

If EMG signal processing is performed without frequency band filtering, then processing speed is faster, but measurement precision decreases due to noise interference

Engineering Contradiction:

Improveprocessing speedVSAvoidsignal accuracy

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

Frequency band filtering is performed as a preliminary step before EMG signal processing to remove noise components outside the relevant frequency range. This pre-processing ensures that subsequent analysis operates on cleaned data, improving measurement precision without significantly impacting overall processing speed

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Analog filtering circuits are replaced with digital signal processing techniques for frequency band filtering. This substitution allows for more precise control over filtering parameters, better noise rejection, and flexible adjustment of filter characteristics while maintaining processing efficiency

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Device complexity

If simple EMG signal comparison is used for authentication, then processing is simpler and faster, but reliability of authentication decreases

Engineering Contradiction:

Improveprocessing complexityVSAvoidauthentication reliability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The authentication process is divided into multiple stages: signal acquisition, frequency band filtering, feature extraction (including time-domain and frequency-domain analysis), and pattern matching against stored templates. This segmentation allows for comprehensive analysis while maintaining organized and manageable processing steps

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Multiple EMG signal parameters are extracted and analyzed (including amplitude, frequency, waveform characteristics) rather than relying on a single simple metric. This excessive analysis of signal characteristics ensures high authentication reliability by capturing the unique muscular electrical patterns of each individual

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11436308B2Electromyogram signal-based user authentication apparatus and method

Publication Date: 2022.09.06 IND ACADEMIC COOP FOUND YONSEI UNIV

AI summary

Provided is an electromyogram (EMG) signal-based user authentication apparatus and method. The apparatus includes an EMG signal receiver configured to receive an EMG signal measured using an EMG sensor, a pre-processor configured to remove a partial signal from the received EMG signal according to a preset frequency band, and a controller configured to authenticate a user by comparing a pre-stored EMG signal with the EMG signal in which the partial signal has been removed.