A myoelectric digital twin for fast and realistic modelling in deep learning

• Published in: Nature communications Vol. 14; no. 1; pp. 1600 - 15
• Main Authors: Maksymenko, Kostiantyn, Clarke, Alexander Kenneth, Mendez Guerra, Irene, Deslauriers-Gauthier, Samuel, Farina, Dario
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 23.03.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 631/57/2266; 639/166/987; Algorithms; Computer applications; Computer Science; Computer Simulation; Data augmentation; Deep Learning; Digital twins; Electromyography; Electrophysiology; Human motion; Humanities and Social Sciences; Humans; Interfaces; Learning algorithms; Machine learning; Man-machine interfaces; Modeling and Simulation; multidisciplinary; Muscle, Skeletal - physiology; Myoelectricity; Robotics; Science; Science (multidisciplinary); Simulation; Training; Virtual reality; biophysical simulation; machine learning; electromyography; human-machine interface
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-37238-w

Muscle electrophysiology has emerged as a powerful tool to drive human machine interfaces, with many new recent applications outside the traditional clinical domains, such as robotics and virtual reality. However, more sophisticated, functional, and robust decoding algorithms are required to meet the fine control requirements of these applications. Deep learning has shown high potential in meeting these demands, but requires a large amount of high-quality annotated data, which is expensive and time-consuming to acquire. Data augmentation using simulations, a strategy applied in other deep learning applications, has never been attempted in electromyography due to the absence of computationally efficient models. We introduce a concept of Myoelectric Digital Twin - highly realistic and fast computational model tailored for the training of deep learning algorithms. It enables simulation of arbitrary large and perfectly annotated datasets of realistic electromyography signals, allowing new approaches to muscular signal decoding, accelerating the development of human-machine interfaces. Muscle electrophysiology is a promising tool for human-machine approaches in medicine and beyond clinical applications. The authors propose here a model simulating electric signals produced during human movements and apply this data for training of deep learning algorithms.