EMG Pattern Recognition via Bayesian Inference with Scale Mixture-Based Stochastic Generative Models

TL;DR

This paper introduces a Bayesian generative model for EMG pattern recognition that accounts for signal uncertainty, demonstrating improved classification accuracy over traditional methods through simulations and real data analysis.

Contribution

It proposes a scale mixture-based stochastic EMG model trained with variational Bayesian learning, incorporating hyperparameter optimization via mutual information, advancing EMG classification techniques.

Findings

Outperforms conventional classifiers on public EMG datasets.

Demonstrates the relationship between hyperparameters and classification accuracy.

Validates the proposed model's effectiveness through simulations and real EMG analysis.

Abstract

Electromyogram (EMG) has been utilized to interface signals for prosthetic hands and information devices owing to its ability to reflect human motion intentions. Although various EMG classification methods have been introduced into EMG-based control systems, they do not fully consider the stochastic characteristics of EMG signals. This paper proposes an EMG pattern classification method incorporating a scale mixture-based generative model. A scale mixture model is a stochastic EMG model in which the EMG variance is considered as a random variable, enabling the representation of uncertainty in the variance. This model is extended in this study and utilized for EMG pattern classification. The proposed method is trained by variational Bayesian learning, thereby allowing the automatic determination of the model complexity. Furthermore, to optimize the hyperparameters of the proposed method with a partial discriminative approach, a mutual information-based determination method is introduced. Simulation and EMG analysis experiments demonstrated the relationship between the hyperparameters and classification accuracy of the proposed method as well as the validity of the proposed method. The comparison using public EMG datasets revealed that the proposed method outperformed the various conventional classifiers. These results indicated the validity of the proposed method and its applicability to EMG-based control systems. In EMG pattern recognition, a classifier based on a generative model that reflects the stochastic characteristics of EMG signals can outperform the conventional general-purpose classifier.