Abstract
Force myography (FMG) detects hand gestures based on muscular contractions, featuring as an alternative to surface electromyography. However, typical FMG systems rely on spatially-distributed arrays of force-sensing resistors to resolve ambiguities. The aim of this proof-of-concept study is to develop a method for identifying hand poses from the static and dynamic components of FMG waveforms based on a compact, single-channel optical fiber sensor. As the user performs a gesture, a micro-bending transducer positioned on the belly of the forearm muscles registers the dynamic optical signals resulting from the exerted forces. A Raspberry Pi 3 minicomputer performs data acquisition and processing. Then, convolutional neural networks correlate the FMG waveforms with the target postures, yielding a classification accuracy of (93.98 ± 1.54)% for eight postures, based on the interrogation of a single fiber transducer.
Funder
Sao Paulo Research Foundation
FAPESP CEPID Brainn, Grant Number
Conselho Nacional de Desenvolvimento Cientifico e Tecnologico
Coordenacao de Pessoal de Nivel Superior
Subject
General Environmental Science
Reference39 articles.
1. Neural feedback strategies to improve grasping coordination in neuromusculoskeletal prostheses;Sci. Rep.,2020
2. Using EMG signals to assess proximity of instruments to nerve roots during robot-assisted spinal surgery;Int. J. Med. Robot.,2022
3. Comparisons between end-effector and exoskeleton rehabilitation robots regarding upper extremity function among chronic stroke patients with moredare-to-severe upper limb impairment;Sci. Rep.,2020
4. Kim, M., Jeon, C., and Kim, J. (2017). A study on immersion and presence of a portable hand haptic system for immersive virtual reality. Sensors, 17.
5. Connolly, J., Condell, J., Curran, K., and Gardiner, P. (2022). Improving data glove accuracy and usability using a neural network when measuring finger joint range of motion. Sensors, 22.