Wearable Biosignal Gesture Recognition via Motion Artifact Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current gesture recognition technologies face challenges in accurately recognizing user gestures without misinterpretation, particularly when using EMG sensors, which require attachment to the skin and can lead to incorrect recognition of unintentional gestures, and they often rely on additional sensors like accelerometers and gyroscopes, increasing power consumption and production costs.

Innovation Solution

A method and apparatus that utilize a biosignal sensor, such as a PPG or ECG sensor, to detect motion artifacts from intentional user movements or pressure applied to the sensor, allowing for gesture recognition without additional sensors, by comparing signal patterns to pre-registered reference patterns to control functions in wearable devices or connected devices like smartphones and IoT devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If EMG sensors are used for gesture recognition, then gesture detection capability is improved, but the likelihood of misrecognizing unintentional gestures increases and device complexity increases

Engineering Contradiction:
Improvegesture detection accuracyVSAvoidgesture recognition accuracy
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent introduces motion artifacts as an intermediary phenomenon that occurs when users intentionally press or move the wearable device. These motion artifacts serve as a mediator between the user's intentional gesture and the biosignal sensor, creating a detectable signal pattern that distinguishes intentional gestures from unintentional movements. The motion artifact processing unit specifically detects these intermediary signals to enable accurate gesture recognition.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the detection parameter from direct muscle signal detection (EMG) to motion artifact detection in biosignal. By monitoring changes in biosignal caused by motion artifacts rather than directly detecting muscle electrical activity, the system achieves more reliable distinction between intentional and unintentional gestures, as motion artifacts only occur with deliberate physical interaction.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If additional sensors like accelerometers and gyroscopes are added for gesture recognition, then gesture detection capability is improved, but power consumption increases

Engineering Contradiction:
Improvegesture detection accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent makes the biosignal sensor multi-functional by using it for both health monitoring and gesture recognition purposes. The same biosignal sensor that monitors cardiovascular health also detects motion artifacts for gesture control, eliminating the need for separate gesture detection sensors and thereby reducing overall power consumption while maintaining gesture detection capability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Measurement precision

If additional sensors like accelerometers and gyroscopes are added for gesture recognition, then gesture detection capability is improved, but production costs increase

Engineering Contradiction:
Improvegesture detection accuracyVSAvoidproduction cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent makes the biosignal sensor multi-functional by using it for both health monitoring and gesture recognition purposes. The same biosignal sensor that monitors cardiovascular health also detects motion artifacts for gesture control, eliminating the need for separate gesture detection sensors and thereby reducing overall power consumption while maintaining gesture detection capability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent merges the gesture recognition function with the existing health monitoring biosignal sensor. By combining these functions into a single sensor system, the patent reduces the total number of components needed, simplifying manufacturing and reducing production costs while maintaining comprehensive functionality.

Inventive Principle:
Principle #5Merging (Combining)

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

This approach reduces the likelihood of misrecognizing unintentional gestures and decreases power consumption and production costs by eliminating the need for EMG sensors, while enabling intuitive gesture control of various devices through wearable biosignal sensors.

Implementation Method 1

detecting, using a processor, a motion artifact from an output signal of a biosignal sensor

Methodology Applied
Scientific EffectMotion artifact detection:

Implementation Method 2

The biosignal sensor may be configured to measure a biosignal including at least one of a photoplethysmogram (PPG) signal

Methodology Applied
Scientific EffectPhotoplethysmogram: Absorption (EM radiation)

Implementation Method 3

The biosignal sensor may be configured to measure a biosignal including at least one of a photoplethysmogram (PPG) signal and an electroc8ardiogram (ECG) signal

Methodology Applied
Scientific EffectElectrocardiogram: Conduction (electrical)

Data Source

PatentEP3171248B1Gesture recognition method, apparatus and wearable device
Publication Date: 2020.04.08 SAMSUNG ELECTRONICS CO LTD
  • EP3171248B1 patent drawingFigure 1
  • EP3171248B1 patent drawingFigure 2
  • EP3171248B1 patent drawingFigure 3

AI summary

A method and an apparatus for gesture recognition and a wearable device for gesture recognition are described. A method of gesture recognition involves using a processor to detect a motion artifact from an output signal of a biosignal sensor and generating a control signal to control a function of a target device that corresponds to a reference signal pattern in response to a signal pattern of the detected motion artifact corresponding to the reference signal pattern.