VAE-Based Synthetic EMG Generation with Mix-Consistency Loss for Recognizing Unseen Motion Combinations

TL;DR

This paper introduces a VAE-based method with a mix-consistency loss to generate synthetic EMG signals for recognizing complex, unseen motion combinations, significantly improving classification accuracy over previous linear combination approaches.

Contribution

The paper presents a novel structured latent space learning approach for synthetic EMG generation that captures complex neuromuscular phenomena, enhancing unseen motion recognition.

Findings

Achieved approximately 30% accuracy improvement in upper-limb motion classification.

Outperformed input-space synthesis methods in generating realistic combined EMG patterns.

Validated on data from eight healthy participants.

Abstract

Electromyogram (EMG)-based motion classification using machine learning has been widely employed in applications such as prosthesis control. While previous studies have explored generating synthetic patterns of combined motions to reduce training data requirements, these methods assume that combined motions can be represented as linear combinations of basic motions. However, this assumption often fails due to complex neuromuscular phenomena such as muscle co-contraction, resulting in low-fidelity synthetic signals and degraded classification performance. To address this limitation, we propose a novel method that learns to synthesize combined motion patterns in a structured latent space. Specifically, we employ a variational autoencoder (VAE) to encode EMG signals into a low-dimensional representation and introduce a mixconsistency loss that structures the latent space such that combined motions are embedded between their constituent basic motions. Synthetic patterns are then generated within this structured latent space and used to train classifiers for recognizing unseen combined motions. We validated our approach through upper-limb motion classification experiments with eight healthy participants. The results demonstrate that our method outperforms input-space synthesis approaches, achieving approximately 30% improvement in accuracy.