Learning Model for Masticatory Side Determination

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Long-term monitoring of muscle activities for mastication habits is affected by noise contamination, particularly with cloth electrodes, and skin impedance changes, leading to unreliable determination of the masticatory side due to variations in myoelectric potential measurements.

Innovation Solution

A learning model generation apparatus that calculates correlation coefficients and power spectrum features from electromyographic waveforms from both left and right masticatory muscles, generating a learning model to determine the masticatory side, while performing abnormal value determination to exclude noisy data, using unsupervised learning to discern between normal and abnormal values.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If myoelectric potential amplitude is used as an indicator to determine masticatory side, then the determination can be made based on muscle activity, but the reliability degrades due to noise contamination and skin impedance changes

Engineering Contradiction:

Improvereliability of masticatory side determinationVSAvoidprecision of myoelectric potential measurement

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The invention changes the measurement parameters from amplitude-based myoelectric potential to frequency-based power spectrum analysis. By transforming the signal into the frequency domain and extracting features from the power spectrum, the system becomes less sensitive to amplitude variations caused by skin impedance and noise, thereby improving measurement precision and reliability

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The invention introduces an intermediary processing step (Fourier transform and power spectrum calculation) between the raw myoelectric signal and the final determination. This intermediary transformation acts as a mediator that filters out noise and impedance-related artifacts while preserving the essential masticatory side information

Inventive Principle:

Principle #24Intermediary (Mediator)

2Duration of action of stationary object

If cloth electrodes are used for long-term monitoring, then continuous monitoring is possible, but noise contamination significantly affects estimation results

Engineering Contradiction:

Improveduration of monitoringVSAvoidreliability of estimation results

Core Design Contradiction:

Duration of action of stationary objectVSReliability

Solution Approach 1:

The invention converts the harmful noise contamination into a distinguishable feature through power spectrum analysis. By transforming the signal to the frequency domain, noise appears as distinct spectral patterns that can be differentiated from genuine masticatory muscle activity, allowing the system to maintain reliability even with cloth electrodes used for long-term monitoring

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

3Ease of operation

If skin impedance changes due to humidity and sweat, then the electrodes remain in contact with skin, but the amplitude of myoelectric potential changes leading to erroneous determination

Engineering Contradiction:

Improveease of electrode placementVSAvoidprecision of myoelectric potential amplitude

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The invention changes from measuring amplitude (which is sensitive to skin impedance) to measuring frequency characteristics from power spectrum (which is robust to impedance changes). This parameter transformation eliminates the erroneous amplitude variations caused by humidity and sweat, maintaining measurement precision while keeping electrodes in continuous contact with the skin

Inventive Principle:

Principle #35Parameter changes

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 a reliable method for determining the masticatory side by using robust feature values, reducing the impact of skin impedance and noise, and minimizing processing load, resulting in accurate and reliable masticatory side determination.

Implementation Method 1

calculate a second feature value for learning, from a power spectrum obtained by performing frequency analysis on the first electromyographic waveform; calculate a third feature value for learning, from a power spectrum obtained by performing frequency analysis on the second electromyographic waveform

Methodology Applied

Scientific EffectFrequency analysis:

Data Source

PatentUS11596336B2Learning model-generating apparatus, method, and program for assessing favored chewing side as well as determination device, method, and program for determining favored chewing side

Publication Date: 2023.03.07 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

A reliable technology for determining the masticatory side of the user is provided. First and second electromyographic waveforms respectively originating from left and right muscles related to masticatory actions of a user are acquired; a coefficient of correlation between pieces of information respectively extracted from the first and the second electromyographic waveforms is calculated as a first feature value; a second feature value is calculated from a power spectrum obtained by performing frequency analysis on the first electromyographic waveform; a third feature value is calculated from a power spectrum obtained by performing frequency analysis on the second electromyographic waveform; a learning model is generated by associating the first, second, and third feature values with a plurality of labels; and the masticatory side of the user is determined based on first, second, and third feature values calculated from a newly acquired electromyographic waveform and the learning model.