Deep Learning for Robust Decomposition of High-Density Surface EMG Signals

Clarke, Alexander Kenneth; Atashzar, S. Farokh; Vecchio, Alessandro Del; Barsakcioglu, Deren Y.; Muceli, Silvia; Bentley, Paul; Urh, Filip; Holobar, Aleš; Farina, Dario

doi:10.1109/tbme.2020.3006508

Cited by 66 publications

(63 citation statements)

References 29 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensitivity and precision were 84 ± 5% and 93 ± 2%, respectively. Note that we only considered the MUs with a F1-score above 0.7 [19]. As a comparison, a F1-score threshold of 0.8 led to a number of 11 ± 4 identified MUs, 73% of the averaged total number of MUs (i.e.…”

Section: Effect Of Window Size and Step Size On Experimentally Recorded Signalsmentioning

confidence: 99%

A convolutional neural network to identify motor units from high-density surface electromyography signals in real time

et al. 2021

View full text Add to dashboard Cite

Objectives. This paper aims to investigate the feasibility and the validity of applying deep convolutional neural networks (CNN) to identify motor unit (MU) spike trains and estimate the neural drive to muscles from high-density electromyography (HD-EMG) signals in real time. Two distinct deep CNNs are compared with the convolution kernel compensation (CKC) algorithm using simulated and experimentally recorded signals. The effects of window size and step size of the input HD-EMG signals are also investigated. Approach. The MU spike trains were first identified with the CKC algorithm. The HD-EMG signals and spike trains were used to train the deep CNN. Then, the deep CNN decomposed the HD-EMG signals into MU discharge times in real time. Two CNN approaches are compared with the CKC: (a) multiple single-output deep CNN (SO-DCNN) with one MU decomposed per network, and (b) one multiple-output deep CNN (MO-DCNN) to decompose all MUs (up to 23) with one network. Main results. The MO-DCNN outperformed the SO-DCNN in terms of training time (3.2-21.4 s epoch −1 vs 6.5-47.8 s epoch −1 , respectively) and prediction time (0.04 vs 0.27 s sample −1 , respectively). The optimal window size and step size for MO-DCNN were 120 and 20 data points, respectively. It results in sensitivity of 98% and 85% with simulated and experimentally recorded HD-EMG signals, respectively.There is a high cross-correlation coefficient between the neural drive estimated with CKC and that estimated with MO-DCNN (range of r-value across conditions: 0.88-0.95). Significance. We demonstrate the feasibility and the validity of using deep CNN to accurately identify MU activity from HD-EMG with a latency lower than 80 ms, which falls within the lower bound of the human electromechanical delay. This method opens many opportunities for using the neural drive to interface humans with assistive devices.

show abstract

Section: Effect Of Window Size and Step Size On Experimentally Recorded Signalsmentioning

confidence: 99%

A convolutional neural network to identify motor units from high-density surface electromyography signals in real time

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recently, DNNs have been designed and used by our team [9]- [12] and other research groups [13]- [19], for myocontrol, achieving superior classification performance than conventional approaches. For example, in Reference [19], which is among the first DNN-based methods developed for the analysis of sEMG data, it was shown that results of a DNN with a very simple architecture are comparable to the average result of classical methods.…”

Section: Introductionmentioning

confidence: 99%

FS-HGR: Few-Shot Learning for Hand Gesture Recognition via Electromyography

Rahimian

Zabihi

Asif

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

“…However, its use is mostly limited to isometric contractions or slow dynamic contractions, mainly due to computational challenges related to the assumption that motor units are stationary and real-time implementation of the method. Both model-free AI (e.g., machine and deep learning techniques) (Chen et al, 2020 ; Clarke et al, 2020 ) and model-based techniques (e.g., data-driven mechanistic modeling) (Sartori and Sawicki, 2021 ) are explored to enable real-time implementation, which would allow mechanical and neural adaptations to exoskeleton training and neurostimulation to be predicted.…”

Section: Interfacing With the Central Nervous Systemmentioning

confidence: 99%

Adaptation Strategies for Personalized Gait Neuroprosthetics

et al. 2021

View full text Add to dashboard Cite

Personalization of gait neuroprosthetics is paramount to ensure their efficacy for users, who experience severe limitations in mobility without an assistive device. Our goal is to develop assistive devices that collaborate with and are tailored to their users, while allowing them to use as much of their existing capabilities as possible. Currently, personalization of devices is challenging, and technological advances are required to achieve this goal. Therefore, this paper presents an overview of challenges and research directions regarding an interface with the peripheral nervous system, an interface with the central nervous system, and the requirements of interface computing architectures. The interface should be modular and adaptable, such that it can provide assistance where it is needed. Novel data processing technology should be developed to allow for real-time processing while accounting for signal variations in the human. Personalized biomechanical models and simulation techniques should be developed to predict assisted walking motions and interactions between the user and the device. Furthermore, the advantages of interfacing with both the brain and the spinal cord or the periphery should be further explored. Technological advances of interface computing architecture should focus on learning on the chip to achieve further personalization. Furthermore, energy consumption should be low to allow for longer use of the neuroprosthesis. In-memory processing combined with resistive random access memory is a promising technology for both. This paper discusses the aforementioned aspects to highlight new directions for future research in gait neuroprosthetics.

show abstract

Deep Learning for Robust Decomposition of High-Density Surface EMG Signals

Cited by 66 publications

References 29 publications

A convolutional neural network to identify motor units from high-density surface electromyography signals in real time

A convolutional neural network to identify motor units from high-density surface electromyography signals in real time

FS-HGR: Few-Shot Learning for Hand Gesture Recognition via Electromyography

Adaptation Strategies for Personalized Gait Neuroprosthetics

Contact Info

Product

Resources

About