GEGLU-Transformer for IMU-to-EMG Estimation with Few-Shot Adaptation

TL;DR

This paper introduces a GEGLU-Transformer model for estimating muscle activation from inertial data, achieving high accuracy and rapid adaptation with minimal subject-specific data, advancing wearable robotics control.

Contribution

The work presents a novel GEGLU-Transformer architecture that improves cross-subject generalization and enables quick personalization in IMU-to-EMG estimation.

Findings

Achieves r = 0.706 without subject-specific adaptation

Performance improves to r = 0.761 with only 0.5% adaptation data

Demonstrates rapid adaptation and early performance saturation

Abstract

Reliable estimation of neuromuscular activation is a key enabler for adaptive and personalized control in wearable robotics. However, surface electromyography (EMG) remains difficult to deploy robustly outside laboratory settings due to electrode sensitivity, signal non-stationarity, and strong subject dependence. In this work, we propose an adaptive IMU-to-EMG learning framework that reconstructs continuous muscle activation envelopes from wearable inertial measurements across heterogeneous movement conditions. The approach combines a Transformer encoder with Gaussian Error Gated Linear Units (GEGLU-Transformer) to enhance cross-subject generalization and enable rapid subject-specific personalization. Under a strict leave-one-subject-out (LOSO) protocol on a multi-condition lower-limb biomechanics dataset, the proposed architecture achieves r = 0.706 +/- 0.139 and R^2 = 0.474 +/- 0.208 without subject-specific adaptation. With only 0.5% adaptation data, performance increases to r = 0.761 +/- 0.030 and R^2 = 0.559 +/- 0.047, demonstrating rapid adaptation and early performance saturation. These results support attention-based architectures combined with lightweight adaptation as a practical and scalable alternative to direct EMG sensing for real-world wearable robotic applications.