Time2Vec Transformer for Robust Gesture Recognition from Low-Density sEMG

TL;DR

This paper introduces a novel deep learning framework using Time2Vec embeddings and a hybrid Transformer architecture for accurate gesture recognition from minimal sEMG sensors, enabling cost-effective and rapid prosthetic control personalization.

Contribution

It presents a data-efficient Transformer-based model with learnable temporal embeddings and a fusion strategy, achieving state-of-the-art accuracy with minimal sensor hardware and rapid calibration.

Findings

Achieved 95.7% F1-score on a 10-class movement set.

Rapid calibration improved accuracy from 21% to 97%.

Validated temporal embeddings can compensate for low spatial resolution.

Abstract

Accurate and responsive myoelectric prosthesis control typically relies on complex, dense multi-sensor arrays, which limits consumer accessibility. This paper presents a novel, data-efficient deep learning framework designed to achieve precise and accurate control using minimal sensor hardware. Leveraging an external dataset of 8 subjects, our approach implements a hybrid Transformer optimized for sparse, two-channel surface electromyography (sEMG). Unlike standard architectures that use fixed positional encodings, we integrate Time2Vec learnable temporal embeddings to capture the stochastic temporal warping inherent in biological signals. Furthermore, we employ a normalized additive fusion strategy that aligns the latent distributions of spatial and temporal features, preventing the destructive interference common in standard implementations. A two-stage curriculum learning protocol is utilized to ensure robust feature extraction despite data scarcity. The proposed architecture achieves a state-of-the-art multi-subject F1-score of 95.7% $\pm$ 0.20% for a 10-class movement set, statistically outperforming both a standard Transformer with fixed encodings and a recurrent CNN-LSTM model. Architectural optimization reveals that a balanced allocation of model capacity between spatial and temporal dimensions yields the highest stability. Furthermore, while direct transfer to a new unseen subject led to poor accuracy due to domain shifts, a rapid calibration protocol utilizing only two trials per gesture recovered performance from 21.0% $\pm$ 2.98% to 96.9% $\pm$ 0.52%. By validating that high-fidelity temporal embeddings can compensate for low spatial resolution, this work challenges the necessity of high-density sensing. The proposed framework offers a robust, cost-effective blueprint for next-generation prosthetic interfaces capable of rapid personalization.