# Generalizable gesture classification of HDsEMG using volume representations of muscles averaged across multiple individuals

## TL;DR

This paper introduces a 3D muscle model for classifying hand gestures using EMG data, aiming to generalize across individuals and new gesture combinations.

## Contribution

A novel 3D volume model of muscles averaged across individuals for generalizable gesture classification using HDsEMG.

## Key findings

- True positive rates for single-digit extensions ranged from 61.9 to 95.1%.
- The model showed generalizability to new gesture compositions and across subjects.
- Multi-label classification maintained performance while using a leave-one-out approach.

## Abstract

Human hands can perform far more gestures than the number of muscles controlling them, as most gestures result from coordinated combinations of muscle activations and relaxations. This complexity poses a key challenge for human-machine interfaces performing gesture classification based on electromyography (EMG). Rather than identifying all conceivable gestures, it may be simpler to instead identify the activity of the individual muscles which generate a variety of complicated gestures. Here we suggest a three-dimensional model with volume representations of individual digit extensor muscles, averaged across multiple individuals, and evaluate its application and performance in hand gesture classification. Time-domain peaks in high-density surface EMG data from different hand gestures were extracted and localized within the model, from which a gesture classification scheme was generated for both single and multi-label cases. The model was created and tested on a publicly available dataset with 19 participants, leveraging a leave-one-out approach to assess inter-subject generalizability, and multi-label data to assess generalizability to gestures not included in the creation of the model. For single-label classification performance, true positive rates were between 61.9 and 95.1%, with false positive rates between 0 and 24.1%, for different single-digit extensions. The multi-label test demonstrated some degree of generalizability in identifying completely new gesture compositions, while simultaneously maintaining the leave-one-out approach for inter-subject generalizability. A model generated with this approach could be used for gesture classification by anyone, without individual modelling data, with the potential to generalize to any number of gesture compositions.