Novel Wearable HD-EMG Sensor With Shift-Robust Gesture Recognition Using Deep Learning

• Published in: IEEE transactions on biomedical circuits and systems Vol. 17; no. 5; pp. 968 - 984
• Main Authors: Chamberland, Felix, Buteau, Etienne, Tam, Simon, Campbell, Evan, Mortazavi, Ali, Scheme, Erik, Fortier, Paul, Boukadoum, Mounir, Campeau-Lecours, Alexandre, Gosselin, Benoit
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Arrays; Artificial intelligence (AI); Artificial neural networks; biomedical; Classification; Convolutional neural networks; Data augmentation; Deep Learning; Density; Electrodes; Electromyography; electromyography (EMG); flexible PCB; Forearm; Forearm - physiology; Gesture recognition; Gestures; hand gesture recognition (HGR); HD-EMG; Humans; Machine learning; Muscles; Myoelectric control; Myoelectricity; Neural networks; prosthesis control; Robustness; Robustness (mathematics); Rotation; Sensors; Wearable Electronic Devices; Wearable technology
• ISSN: 1932-4545; 1940-9990; 1940-9990
• DOI: 10.1109/TBCAS.2023.3314053

In this work, we present a hardware-software solution to improve the robustness of hand gesture recognition to confounding factors in myoelectric control. The solution includes a novel, full-circumference, flexible, 64-channel high-density electromyography (HD-EMG) sensor called EMaGer. The stretchable, wearable sensor adapts to different forearm sizes while maintaining uniform electrode density around the limb. Leveraging this uniformity, we propose novel array barrel-shifting data augmentation (ABSDA) approach used with a convolutional neural network (CNN), and an anti-aliased CNN (AA-CNN), that provides shift invariance around the limb for improved classification robustness to electrode movement, forearm orientation, and inter-session variability. Signals are sampled from a 4×16 HD-EMG array of electrodes at a frequency of 1 kHz and 16-bit resolution. Using data from 12 non-amputated participants, the approach is tested in response to sensor rotation, forearm rotation, and inter-session scenarios. The proposed ABSDA-CNN method improves inter-session accuracy by 25.67% on average across users for 6 gesture classes compared to conventional CNN classification. A comparison with other devices shows that this benefit is enabled by the unique design of the EMaGer array. The AA-CNN yields improvements of up to 63.05% accuracy over non-augmented methods when tested with electrode displacements ranging from −45<inline-formula><tex-math notation="LaTeX">^\circ</tex-math></inline-formula> to +45<inline-formula><tex-math notation="LaTeX">^\circ</tex-math></inline-formula> around the limb. Overall, this article demonstrates the benefits of co-designing sensor systems, processing methods, and inference algorithms to leverage synergistic and interdependent properties to solve state-of-the-art problems.