A Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals

Jul 16, 2026

For seamless control of advanced hand prostheses and augmented reality systems, accurate real-time hand gesture recognition is essential. This work presents a graph-network-based sEMG representation that encodes forearm muscle activation patterns as graphs. A graph neural network model enables real-time hand gesture classification from sEMG signals collected using a myoband with 8 electrodes around the forearm. Experiments with 8 healthy subjects achieve 99% average classification accuracy and 48 ms for graph construction and prediction on an M1 Pro CPU, outperforming state-of-the-art methods.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

Abstract

Introduction

Methodology

Overview

A Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals Pragatheeswaran Vipulanandan, Kamal Premaratne, Manohar Murthi Department of Electrical and Computer Engineering University of Miami Coral Gables, Florida, USA [pxv245@miami.edu](pxv245@miami.edu), [kamal@miami.edu](kamal@miami.edu), [mmurthi@miami.edu](mmurthi@miami.edu) arXiv :2607 .07850v 1 [ cs .AI] 8 Jul 2026 Abstract—For seemless control of advanced hand prostheses and augmented reality, accurate and immediate hand gestures recognition is essential. Surface electromyography (sEMG) signals obtained from the forearm are commonly employed for this purpose. In this paper, we present a novel approach for sEMG representation that utilizes graph networks which contain information about muscle activation patterns in the forearm. Based on these graph networks, we have developed a machine learning algorithm capable of real-time hand gesture recognition using a graph neural network. The algorithm’s performance was evaluated using sEMG signals acquired from myoband, which has 8 electrodes placed around the forearm, involving 8 healthy subjects. The proposed method demonstrated an average classification accuracy of 99%, surpassing the performance of state-ofthe-art techniques. The average time for both graph construction and prediction stood at 48ms utilizing a M1 pro CPU, rendering the approach well-suited for real-time applications. Index Terms—Graph neural networks, gesture recognition, sEMG signals I. INTRODUCTION In the realm of human-computer interaction, real-time gesture recognition plays a pivotal role in enabling seamless communication between humans and machines. The ability to interpret human gestures accurately and swiftly holds immense potential for applications ranging from virtual reality (VR) and augmented reality (AR) systems to healthcare and robotics. Some of these systems utilize surface electromyogram (sEMG) signals which are captured from the forearm [1], [2] . The prevalent approach for gesture recognition involves extracting temporal and frequency domain features from the acquired sEMG recordings and subsequently classifying them using various learning algorithms, such as support vector machines (SVMs), linear discriminant analysis (LDA), and neural networks (NNs) [3]–[7] . While numerous studies have been conducted to accurately classify hand gestures from pre-recorded sEMG signals [4],[8], [9], only a limited number of research works have concentrated on real-time hand gesture recognition using sEMG signals from the forearm [10]–[12] . The majority of existing methods utilize binning of sEMG signals and extracting specific features of the wave within each bin for classification This work is based on research supported by the National Science Foundation Grant \#2123635 and the University of Miami Provost Fellowship in Interdisciplinary Computing. purposes [9]–[11],[13] . Thus, the issue of computational complexity arising from continuous binning poses a challenge for real-time gesture prediction. In response to these challenges, this paper introduces an innovative approach harnessing the power of graph theory for real-time gesture recognition. The motivation for this research is rooted in the need for robust and efficient gesture recognition systems that can operate in realtime, allowing for natural and intuitive interactions between humans and digital interfaces. Graph-based methods offer a versatile framework for modeling complex relationships and patterns within data, making them ideally suited for capturing the spatial and temporal dynamics of gestures [14] . By representing gestures as dynamic graphs, we bridge the gap between raw sensor data and meaningful gesture representations. Each gesture is conceptualized as a graph, with nodes representing the electrodes on the human body and edges capturing the temporal dependencies and spatial correlations between the nodes [11] . Traditional graph

FAQs

What signals and sensors are used for the real-time gesture recognition task?

The method uses surface electromyography (sEMG) signals acquired from a myoband placed around the forearm with 8 electrodes.

How does the model represent sEMG data for the graph neural network?

Each gesture is transformed into a graph where electrodes are nodes, and edges capture information such as muscle activation patterns and correlations from time-series sEMG.

What performance and latency does the proposed approach achieve?

Experiments report an average classification accuracy of 99%, with average time for graph construction and prediction of 48 ms on an M1 Pro CPU.

Jul 16, 2026

Upload by Clementine