Lower Arm Electromyography (EMG) Activity Detection Using Local Binary Patterns

McCool, Paul; Chatlani, Navin; Petropoulakis, Lykourgos; Soraghan, John J.; Menon, Radhika; Lakany, Heba

doi:10.1109/tnsre.2014.2320362

Cited by 22 publications

(23 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large body of work has addressed the specific problem of EMG-based inference of wrist-hand movements. In [24], three hand motions are differentiated using 1D Local Binary Pattern (LBP) feature extraction. Four sensors are used in [15] to detect seven wrist-hand movements using time and frequency domain features with SVM classification, whilst [22] also uses four sensors on the lower and upper forearm to classify six wrist-hand motions with accuracy between 87 -97%.…”

Section: A Wrist-hand Movement Detection Using Emgmentioning

confidence: 99%

Real-Time Embedded EMG Signal Analysis for Wrist-Hand Pose Identification

Raurale

McAllister

Rincón

2020

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

Electromyographic (EMG) signals sensed on the forearm skin surface, when placed over specific muscles, enable a wide range of wrist-hand movements to be accurately detected via complex time-frequency EMG analysis. This capability, however is not available for EMG wearables, which sense EMG from random positions and experience substantially reduced detection performance as a result. In addition, the complexity of the time-frequency analysis process currently precludes real-time detection using the simple embedded processors on EMG wearables is not possible. This paper describes an approach which resolves both these shortcomings. It shows that, when random sensor placement is adopted, wrist-hand movement detection with performance equal the state-of-the-art can be achieved, with only 10% of the computational complexity. This latter property allows the first real-time wrist-hand movement detector using only simple embedded processors; specifically when using on ARM Cortex-A53 processor, execution time is lowered by 90% against the state-of-the-art, with no reduction in detection performance. It is shown how this can be further reduced by 30% by using fewer EMG channels or features, whilst maintaining good detection performance. To the best of the authors' knowledge, this is the first record of real-time high-performance wristhand movement detection for standalone, battery-powered EMG wearables.

show abstract

Section: A Wrist-hand Movement Detection Using Emgmentioning

confidence: 99%

Real-Time Embedded EMG Signal Analysis for Wrist-Hand Pose Identification

Raurale

McAllister

Rincón

2020

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

show abstract

“…The approach in [2] uses the Delsys myoelectric system for EMG acquisition from four forearm muscles and employs Local Discriminant Basis with Wavelet Packet Transform for feature extraction, Principal Component Analysis (PCA) for feature projection and Multi-layer Perceptron (MLP) classification. In [7] an Ottobock acquisition system acquires EMG from two forearm muscles to classify three hand motions using one-dimensional Local Binary Pattern feature extraction. MyoScan EMG sensors are used in [10] to sense four forearm muscles classifying four hand motions using a variety of time/frequency features with PCA and Linear Discriminant Analysis (LDA) for feature projection and classification.…”

Section: Related Workmentioning

confidence: 99%

EMG Wrist-hand Motion Recognition System for Real-time Embedded Platform

Raurale

McAllister

Rincón

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Electromyography (EMG) signal analysis is a popular method for controlling prosthetic and gesture control equipment. For portable systems, such as prosthetic limbs, real-time lowpower operation on embedded processors is critical, but to date there has been no record of how existing EMG analysis approaches support such deployments. This paper presents a novel approach to time-domain classification of multichannel EMG signals harnessed from randomly-placed sensors according to the wrist-hand movements which caused their occurrence. It shows how, by employing a very small set of time-domain features, Kernel Fisher discriminant feature projection and Radial Bias Function neural network classifiers, nine wrist-hand movements can be detected with accuracy exceeding 99% -surpassing the state-of-the-art on record. It also shows how, when deployed on ARM Cortex-A53, the processing time is not only sufficient to enable real-time processing but is also a factor 50 shorter than the leading time-frequency techniques on record.

show abstract

“…1) The LWT [38], EEG [39], [40], ECG [41], [42], and sEMG signals [43], but not in the context of iEMG classification. 4) MLPNN classifier outputs are refined with BMMV in a unique manner.…”

Section: Introductionmentioning

confidence: 99%

Robust Classification of Intramuscular EMG Signals to Aid the Diagnosis of Neuromuscular Disorders

Jose

George

Subathra

et al. 2020

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

This article presents the design and validation of an accurate automatic diagnostic system to classify intramuscular EMG (iEMG) signals into healthy, myopathy, or neuropathy categories to aid the diagnosis of neuromuscular diseases. Methods: First, an iEMG signal is decimated to produce a set of "disjoint" downsampled signals, which are decomposed by the lifting wavelet transform (LWT). The Higuchi's fractal dimensions (FDs) of LWT coefficients in the subbands are computed. The FDs of LWT subband coefficients are fused with one-dimensional local binary pattern derived from each downsampled signal. Next, a multilayer perceptron neural network (MLPNN) determines the class labels of downsampled signals. Finally, the sequence of class labels is fed to the Boyer-Moore majority vote (BMMV) algorithm, which assigns a class to every iEMG signal. Results: The MLPNN-BMMV classifier was experimented with 250 iEMG signals belonging to three categories. The performance of the classifier was validated in comparison with state-of-the-art approaches. The MLPNN-BMMV has resulted in impressive performance measures (%) using a 10-fold cross-validation-accuracy = 99.87 ± 0.25, sensitivity (normal) = 99.97 ± 0.13, sensitivity (myopathy) = 99.68 ± 0.95, sensitivity (neuropathy) = 99.76 ± 0.66, specificity (normal) = 99.72 ± 0.61, specificity (myopathy) = 99.98 ± 0.10, and specificity (neuropathy) = 99.96 ± 0.14-surpassing the existing approaches. Conclusions: A future research direction is to validate the classifier performance with diverse iEMG datasets, which would lead to the design of an affordable real-time expert system for neuromuscular disorder diagnosis. Index Terms-Fractal dimension, intramuscular electromyography, lifting wavelet transform, local binary pattern, majority vote, multilayer perceptron neural network, neuromuscular disorders. Impact Statement-An iEMG classifier is designed and validated with iEMG signals from healthy, myopathy, and neuropathy subjects. The classifier's outstanding performance is a step toward real-time diagnostic system for neuromuscular diseases.

show abstract

Lower Arm Electromyography (EMG) Activity Detection Using Local Binary Patterns

Cited by 22 publications

References 13 publications

Real-Time Embedded EMG Signal Analysis for Wrist-Hand Pose Identification

Real-Time Embedded EMG Signal Analysis for Wrist-Hand Pose Identification

EMG Wrist-hand Motion Recognition System for Real-time Embedded Platform

Robust Classification of Intramuscular EMG Signals to Aid the Diagnosis of Neuromuscular Disorders

Contact Info

Product

Resources

About