Novel approach for electromyography-controlled prostheses based on facial action

Abstract

Individuals with severe tetraplegia frequently require to control their complex assistive devices using body movement with the remaining activity above the neck. Electromyography (EMG) signals from the contractions of facial muscles enable people to produce multiple command signals by conveying information about attempted movements. In this study, a novel EMG-controlled system based on facial actions was developed. The mechanism of different facial actions was processed using an EMG control model. Four asymmetric and symmetry actions were defined to control a two-degree-of-freedom (2-DOF) prosthesis. Both indoor and outdoor experiments were conducted to validate the feasibility of EMG-controlled prostheses based on facial action. The experimental results indicated that the new paradigm presented in this paper yields high performance and efficient control for prosthesis applications.

Face-Computer Interface (FCI): Intent Recognition Based on Facial Electromyography (fEMG) and Online Human-Computer Interface With Audiovisual Feedback

“…There are many factors that affect the performance of the online control stage. These factors include: (1) the accuracy of intention recognition; (2) whether the feedback information is sufficient, such as whether there is voice feedback; (3) whether the actions of the participants are consistent with their intentions; (4) the participant's reaction speed, such as the time it takes to correct the movement or recognition error; (5) the participant's path planning and control strategy for the movement of the gripper (Nam et al, 2014;Zhang et al, 2020). As shown in Figure 11, the accuracy rate from subjects S3, S5, or s2 was lower than that from S4, but in the online process, the former performed better than the latter.…”

“…Nam et al (2014) integrated multiple signals such as EOG and fEMG to control a humanoid robot. Zhang et al (2020) controlled a two-degree-of-freedom (2-DOF) prosthesis based on fEMG. Bastos-Filho et al (2014) and Tamura et al (2012) used fEMG to control the movements of a wheelchair.…”

Lower limb exoskeleton robot and its cooperative control: A review, trends, and challenges for future research

“…When there is active movement present, spasticity usually manifests. Fortunately, the electromyography (EMG) approach (Zhang et al, 2020 ) can be used to recognize or detect its evaluation of muscle activity. Human-robot linkage or coupling and biomechanics have mainly been carried out with rigid exoskeletons, which significantly increase the challenging inertia to the lower extremities and can result in various constraints to the user's normal kinematics (Wang and Lu, 2022 ).…”

An asynchronous artifact-enhanced electroencephalogram based control paradigm assisted by slight facial expression

“…From the aspect of neurophysiology, the mechanism of facial expression had been studied ( Li R. et al, 2018 ) and the functional connectivity analysis was conducted ( Lu Z. F. et al, 2018 ), which revealed the separability of facial-expression assisted brain signals and guided the signal processing. When performing facial expressions, our previous study proved that both the EEG component and the electromyogram (EMG) component can be detected by the EEG electrodes at the same time, and each component can be decoded to provide the instruction for external device operation ( Li R. et al, 2018 ; Zhang et al, 2020 ). Benefiting from the coexistence of EEG and EMG components, enhanced by the EMG artifacts within EEG band, without separating these components, it enabled the capability for real-time decoding and control (each output generated from the latest 100 ms inputs) ( Lu Z. F. et al, 2018 ), and realized the semi-asynchronous logic ( Lu et al, 2020 ).…”