Adaptive Spatial Filtering of High-Density EMG for Reducing the Influence of Noise and Artefacts in Myoelectric Control

Stachaczyk, Martyna; Atashzar, S. Farokh; Farina, Dario

doi:10.1109/tnsre.2020.2986099

Cited by 31 publications

(19 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results obtained without decoding the neural activity were consistent with those reported in previous studies (15) and indicate poor classification performance. Conversely, the proposed neural decoding allowed for >95% accuracy over ten finger tasks at multiple force levels, which was substantially greater than without decoding the tendon signals as well as than conventional EMG-based interfaces (16,17,41).…”

Section: User Intent Prediction (Offline)mentioning

confidence: 94%

Non-invasive real-time access to the output of the spinal cord via a wrist wearable interface

Guerra

Barsakcioglu²,

Vujaklija³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Despite the promising features of neural interfaces, their trade-off between information transfer and invasiveness has limited translation and viability outside research settings. Here, we present a non-invasive neural interface that provides access to spinal motoneuron activities from a sensor band at the wrist. The interface decodes electric signals present at the tendon endings of the forearm muscles by using a model of signal generation and deconvolution. First, we evaluated the reliability of the interface to detect motoneuron firings, and thereafter we used the decoded neural activity for the prediction of finger movements in offline and real-time conditions. The results showed that motoneuron activity decoded from the wrist accurately predicted individual and combined finger commands and therefore allowed for highly accurate real-time control. These findings demonstrate the feasibility of a wearable, non-invasive, neural interface at the wrist for precise real-time control based on the output of the spinal cord.

show abstract

Section: User Intent Prediction (Offline)mentioning

confidence: 94%

Non-invasive real-time access to the output of the spinal cord via a wrist wearable interface

Guerra

Barsakcioglu²,

Vujaklija³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several studies have evaluated the effect of thermal noise, electrode noise, power line interference etc. in surface electromyography based systems for gesture recognition [30], [31], [32]. Similarly, ultrasound signals are also affected by inherent noise due to speckle.…”

Section: Sonomyonet Can Accurately Predict Force In the Presence Of S...mentioning

confidence: 99%

SonoMyoNet: A Convolutional Neural Network for Predicting Isometric Force From Highly Sparse Ultrasound Images

Kamatham

Alzamani

Dockum

et al. 2022

Preprint

View full text Add to dashboard Cite

Ultrasound imaging or sonomyography has been found to be a robust modality for sensing muscle activity due to its ability to directly image deep-seated muscles while providing superior spatiotemporal specificity compared to surface electromyography-based techniques. Quantifying the morphological changes during muscle activity involves computationally expensive approaches to track muscle anatomical structures or extracting features from B-mode images and A-mode signals. In this paper an offline regression convolutional neural network (CNN) called SonoMyoNet for estimating continuous isometric force from sparse ultrasound scanlines has been presented. SonoMyoNet learns features from a few equispaced scanlines selected from B-mode images and utilizes the learned features to accurately estimate continuous isometric force. The performance of SonoMyoNet was evaluated by varying the number of scanlines to simulate the placement of multiple single element ultrasound transducers in a wearable system. Results showed that SonoMyoNet could accurately predict isometric force with just four scanlines and is immune to speckle noise and shifts in the scanline location. Thus, the proposed network reduces the computational load involved in feature tracking algorithms and estimates muscle force from global features of sparse ultrasound images.

show abstract

“…In order to enhance the signal quality, Stachaczyk et al [17] proposed a preprocessing step, which weights the sEMG signal adaptively, to enhance the quality of a signal for a specific time interval. This technique attenuates noise from multi-channel electrodes, the so-called spatial filtering, which yields a high spatial resolution [18].…”

Section: Noise Reduction In Emg Signalsmentioning

confidence: 99%

Recent Trends in Electromyography Signal Processing of Neuromuscular Diseases: An Outlook

Emimal

Hans²,

Inbamalar³

et al. 2021

Advanced Computing and Intelligent Technologies

View full text Add to dashboard Cite

This paper presents a bibliometric review of several techniques applied to the EMG signals. We reviewed research papers, which were specifically applied for the EMG signals. The EMG signal contains a huge amount of data, thus the EMG signal research grabs the significance of advanced techniques and analysis of data, which are capable of handling 'Big Data'. Several noise reduction techniques were discussed and it was found that the wavelet-based noise reduction is a promising technique for EMG classification. More prominent feature extraction and classification techniques and their performance were also reviewed. The modern EMG signal analysis mainly emphasizes feature learning, which is specifically 'deep learning', which combines feature extraction and classification, also to improve classification accuracy. A performance analysis of Convolutional Neural Network (CNN) was done in the later sections.

show abstract

Adaptive Spatial Filtering of High-Density EMG for Reducing the Influence of Noise and Artefacts in Myoelectric Control

Cited by 31 publications

References 44 publications

Non-invasive real-time access to the output of the spinal cord via a wrist wearable interface

Non-invasive real-time access to the output of the spinal cord via a wrist wearable interface

SonoMyoNet: A Convolutional Neural Network for Predicting Isometric Force From Highly Sparse Ultrasound Images

Recent Trends in Electromyography Signal Processing of Neuromuscular Diseases: An Outlook

Contact Info

Product

Resources

About