Proportional and Simultaneous Real-Time Control of the Full Human Hand From High-Density Electromyography

Sîmpetru, Raul; März, Michael; Vecchio, Alessandro Del

doi:10.1109/tnsre.2023.3295060

Cited by 9 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This results in 10 min 8 s training and 2 min 32 s testing data per subject. No validation split was used as our model was validated previously on the same data [3,4] and on new one [5]. Additionally, in order to increase the amount of training data for our model, data augmentation was applied on each EMG segment.…”

Section: Datasetmentioning

confidence: 99%

“…We have evaluated a number of temporal and spatial domain filters, as well as a number of ablations in order to determine whether the prediction capability of the kinematics estimation model [3][4][5] will be affected.…”

Section: Filtersmentioning

confidence: 99%

“…Further, the rectified and low-pass filtered signals, specifically denoted as |Raw|, |5 Hz|, and |20 Hz|, were obtained by first rectifying the raw EMG signal, and subsequently applying the filter. We also added the combination (denoted as Raw + 20 Hz) of the Raw and 20 Hz EMG signal, as we have previously found it to increase the accuracy of our model [3][4][5]. This combination can be seen as a temporal filter with the transfer function of 1 + H low 20 (s) where H low 20 (s) is the transfer function of the 20 Hz lowpass filter.…”

Section: Temporal Filtersmentioning

confidence: 99%

“…We conducted this investigation using an EMG dataset consisting of data from 13 subjects engaged in various hand movements (figure 2). We have recently developed a neural network that is capable of predicting the full kinematics of the human hand at multiple degrees of freedom [3,4] with simultaneous and proportional real-time control [5]. Here, we aimed to investigate the impact of the pre-processing filters and ablation methods on the accuracy of the neural network in predicting hand movements based on the processed EMG signals.…”

Section: Introductionmentioning

confidence: 99%

“…While we have a clear understanding of the intended effects and underlying principles of EMG filters, there is currently a lack of empirical evidence regarding the degree to which these filters preserve the information present in the unfiltered (Raw) EMG signal for estimating hand kinematics. In this work we attempt to answer this question by training the same model proven to work on unfiltered EMG [4,5] following application of diverse temporal and spatial filters.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals ^*

Sîmpetru,

Cnejevici,

Farina

et al. 2024

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Objective: Surface electromyography (sEMG) is a non-invasive technique that records the electrical signals generated by muscles through electrodes placed on the skin. sEMG is the state-of-the-art method used to control active upper limb prostheses because of the association between its amplitude and the neural drive sent from the spinal cord to muscles. However, accurately estimating the kinematics of a freely moving human hand using sEMG from extrinsic hand muscles remains a challenge. Deep learning has been recently successfully applied to this problem by mapping raw sEMG signals into kinematics. Nonetheless, the optimal number of EMG signals and the type of pre-processing that would maximize performance have not been investigated yet. Approach: Here, we analyze the impact of these factors on the accuracy in kinematics estimates. For this purpose, we processed monopolar sEMG signals that were originally recorded from 320 electrodes over the forearm muscles of 13 subjects. We used a previously published deep learning method that can map the kinematics of the human hand with real-time resolution. Main results: While myocontrol algorithms essentially use the temporal envelope of the EMG signal as the only EMG feature, we show that our approach requires the full bandwidth of the signal in the temporal domain for accurate estimates. Spatial filtering however, had a smaller impact and low-order spatial filters may be suitable. Moreover, reducing the number of channels by ablation resulted in large performance losses.The highest accuracy was reached with the highest number of available sensors (n=320). Importantly and unexpected, our results suggest that increasing the number of channels above those used in this study may further enhance the accuracy in predicting the kinematics of the human hand. Significance: We conclude that full bandwidth high-density EMG systems of hundreds of electrodes are needed for accurate kinematic estimates of the human hand.

show abstract

Section: Datasetmentioning

confidence: 99%

Section: Filtersmentioning

confidence: 99%

Section: Temporal Filtersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals ^*

Sîmpetru,

Cnejevici,

Farina

et al. 2024

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

Modulation of Myoelectric Activity by a Virtual Interface of a Prosthetic Hand

Carrillo,

Molinari,

De Villa

et al. 2024

Biosystems &Amp; Biorobotics

View full text Add to dashboard Cite

A multimodal multistream multilevel fusion network for finger joint angle estimation with hybrid sEMG and FMG sensing

Chen,

Gouda,

et al. 2025

Alexandria Engineering Journal

View full text Add to dashboard Cite

Proportional and Simultaneous Real-Time Control of the Full Human Hand From High-Density Electromyography

Cited by 9 publications

References 30 publications

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals ^*

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals ^*

Modulation of Myoelectric Activity by a Virtual Interface of a Prosthetic Hand

A multimodal multistream multilevel fusion network for finger joint angle estimation with hybrid sEMG and FMG sensing

Contact Info

Product

Resources

About

Proportional and Simultaneous Real-Time Control of the Full Human Hand From High-Density Electromyography

Cited by 9 publications

References 30 publications

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals *

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals *

Modulation of Myoelectric Activity by a Virtual Interface of a Prosthetic Hand

A multimodal multistream multilevel fusion network for finger joint angle estimation with hybrid sEMG and FMG sensing

Contact Info

Product

Resources

About

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals ^*

Influence of spatio-temporal filtering on hand kinematics estimation from high-density EMG signals ^*