Classification of Motor Control Difficulty using EMG in Physical Human-Robot Interaction

Manjunatha, Hemanth; Jujjavarapu, Sri Sadhan; Esfahani, Ehsan T.

doi:10.1109/smc42975.2020.9283016

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior studies have already provided evidence of the effectiveness of Riemannian geometry-based classification pipelines in discriminating neural signals based on covariance matrices in motor imagery (Guan et al, 2019;Majidov and Whangbo, 2019), EEG respiratory states (Navarro-Sune et al, 2017), visual evoked potential (Simar et al, 2022), and mental states (Simar et al, 2020) discrimination. While Riemannian geometrybased classification pipelines have primarily been developed and applied to brain-derived signals, such as EEG (Wu et al, 2017) and MEG (Ye et al, 2020), recent work has also used similar pipelines to classify motor control difficulty based on EMG signals (Manjunatha et al, 2020(Manjunatha et al, , 2022. In this work, we further demonstrate their effectiveness at discriminating EMG signals in the context of hand gesture recognition.…”

Section: Pipelines Based On Covariance Matrices and Riemannian Geometrymentioning

confidence: 79%

Machine learning for hand pose classification from phasic and tonic EMG signals during bimanual activities in virtual reality

Simar,

Colot,

Cebolla

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

Myoelectric prostheses have recently shown significant promise for restoring hand function in individuals with upper limb loss or deficiencies, driven by advances in machine learning and increasingly accessible bioelectrical signal acquisition devices. Here, we first introduce and validate a novel experimental paradigm using a virtual reality headset equipped with hand-tracking capabilities to facilitate the recordings of synchronized EMG signals and hand pose estimation. Using both the phasic and tonic EMG components of data acquired through the proposed paradigm, we compare hand gesture classification pipelines based on standard signal processing features, convolutional neural networks, and covariance matrices with Riemannian geometry computed from raw or xDAWN-filtered EMG signals. We demonstrate the performance of the latter for gesture classification using EMG signals. We further hypothesize that introducing physiological knowledge in machine learning models will enhance their performances, leading to better myoelectric prosthesis control. We demonstrate the potential of this approach by using the neurophysiological integration of the “move command" to better separate the phasic and tonic components of the EMG signals, significantly improving the performance of sustained posture recognition. These results pave the way for the development of new cutting-edge machine learning techniques, likely refined by neurophysiology, that will further improve the decoding of real-time natural gestures and, ultimately, the control of myoelectric prostheses.

show abstract

Section: Pipelines Based On Covariance Matrices and Riemannian Geometrymentioning

confidence: 79%

Machine learning for hand pose classification from phasic and tonic EMG signals during bimanual activities in virtual reality

Simar,

Colot,

Cebolla

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

Classification of Motor Control Difficulty using EMG in Physical Human-Robot Interaction

Cited by 1 publication

References 18 publications

Machine learning for hand pose classification from phasic and tonic EMG signals during bimanual activities in virtual reality

Machine learning for hand pose classification from phasic and tonic EMG signals during bimanual activities in virtual reality

Contact Info

Product

Resources

About