Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications

TL;DR

This paper introduces the Spatial Adaptation Layer (SAL), an interpretable method for domain adaptation in biosignal sensor arrays, effectively addressing electrode shift issues with minimal data and high interpretability.

Contribution

The paper presents SAL, a novel domain adaptation layer that learns interpretable affine transformations for biosignal arrays, improving intersession performance with fewer data and enhanced robustness.

Findings

SAL outperforms standard fine-tuning on HD-sEMG datasets.

SAL achieves competitive performance with simple models like logistic regression.

Forearm circumferential translations are key to performance improvements.

Abstract

Machine learning offers promising methods for processing signals recorded with wearable devices such as surface electromyography (sEMG) and electroencephalography (EEG). However, in these applications, despite high within-session performance, intersession performance is hindered by electrode shift, a known issue across modalities. Existing solutions often require large and expensive datasets and/or lack robustness and interpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which can be applied to any biosignal array model and learns a parametrized affine transformation at the input between two recording sessions. We also introduce learnable baseline normalization (LBN) to reduce baseline fluctuations. Tested on two HD-sEMG gesture recognition datasets, SAL and LBN outperformed standard fine-tuning on regular arrays, achieving competitive performance even with a logistic regressor, with orders of magnitude less, physically interpretable parameters. Our ablation study showed that forearm circumferential translations account for the majority of performance improvements.