EMG-based posture classification using a convolutional neural network for a myoelectric hand

Yamanoi, Yusuke; Ogiri, Yosuke; Kato, Ryu

doi:10.1016/j.bspc.2019.101574

Cited by 31 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In EMG pattern recognition, different classifiers are widely used. These are convolutional neural networks (CNNs) [ 42 , 43 ], artificial neural networks (ANNs) [ 1 , 44 ], linear discriminant analysis (LDAs) [ 45 ], support vector machines (SVMs) [ 46 , 47 ], and k-nearest neighbors (KNNs) [ 48 , 49 ]. Among these classifiers, the CNN provides better EMG recognition performance but requires a higher time for learning the model [ 50 ].…”

Section: Methodsmentioning

confidence: 99%

Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees

Ahmad

Haque

et al. 2021

Diagnostics

View full text Add to dashboard Cite

A force-invariant feature extraction method derives identical information for all force levels. However, the physiology of muscles makes it hard to extract this unique information. In this context, we propose an improved force-invariant feature extraction method based on nonlinear transformation of the power spectral moments, changes in amplitude, and the signal amplitude along with spatial correlation coefficients between channels. Nonlinear transformation balances the forces and increases the margin among the gestures. Additionally, the correlation coefficient between channels evaluates the amount of spatial correlation; however, it does not evaluate the strength of the electromyogram signal. To evaluate the robustness of the proposed method, we use the electromyogram dataset containing nine transradial amputees. In this study, the performance is evaluated using three classifiers with six existing feature extraction methods. The proposed feature extraction method yields a higher pattern recognition performance, and significant improvements in accuracy, sensitivity, specificity, precision, and F1 score are found. In addition, the proposed method requires comparatively less computational time and memory, which makes it more robust than other well-known feature extraction methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees

Ahmad

Haque

et al. 2021

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Interface of the developed software for collecting EMGs. [7] 5 New approaches Additional sensors may be needed to increase the functionality of prosthesis control and limit the cognitive load.…”

Section: Figmentioning

confidence: 99%

The Current Status of EMG Signals on Kinematics Needed for Precise Online Myoelectric Control and the Development Direction

Kang

2021

E3S Web Conf.

View full text Add to dashboard Cite

Widely accepted idea is the prosthetic control problem could be regarded as the pattern recognition problem. The prosthetic control means there are several differences such as distinguishable electric signals between different activation of muscle. However, this conventional method could not provide proper control of the artificial limbs. Kinematics behavior is continuous and needs the coordination of multiple physiological degrees of freedom (DOF) among various joints. Currently, a huge challenge is achieving precise, coherent and elegant coordination protheses which needs many DOFs to rehabilitation of patients with limb deficiency. This article analyzed the principles of control of bionic limbs from the aspect of EMG and traditional pattern recognition. According to the research results, the following conclusions can be given. Since the quantum amplitudes are complex numbers generally, different parameter should be included and analyzed together during the quantum information processing. Besides, the quantum control scheme could be combined with the classic one. What is more, other sensor modes should be applied for robust control instead of the EMG signal only.

show abstract

“…Accuracy was calculated as 95% for the DualMyo and 91% for the NinaProDB5 database. Yamanoi et al proposed the CNN model for the development of a myoelectric hand 17 . The method was mounted on a multi‐degree‐of‐freedom myoelectric hand, and EMG signals were obtained from three healthy individuals and one with an amputation.…”

Section: Introductionmentioning

confidence: 99%

Classification of EMG signals taken from arm with hybrid CNN‐SVM architecture

Tuncer

Alkan

2021

Concurrency and Computation

View full text Add to dashboard Cite

Analysis based on the classification of electromyography (EMG) signals, the bioelectrical signs that appear during the contraction of the muscles, can be used in many prosthetic control applications. For this purpose, the classification of the EMG signal is considered a pattern‐recognition problem that can be used to improve the functionality and ease of control of reinforced upper‐limb prostheses. Four different EMG‐signal patterns taken from the biceps and triceps muscles were analyzed via hybrid deep‐learning methods after spectrogram‐based preprocessing. Four hundred EMG spectrograms obtained by preprocessing were classified with hybrid deep‐learning techniques based on AlexNet, GoogLeNet, and ResNet18. The classification was conducted using a support vector machine instead of the classification layers after the pooling layer of deep‐learning architectures used in the hybrid system. In general, acceptable classification results were achieved with all techniques used, and the highest performance was obtained with the hybrid system created with AlexNet architecture. The hybrid‐classification achievements with AlexNet, GoogLeNet, and Resnet18 were 99.17%, 95.83%, and 93.33%, respectively. These results show that the proposed architectures can be used in prosthetic controls created using EMG signals.

show abstract

EMG-based posture classification using a convolutional neural network for a myoelectric hand

Cited by 31 publications

References 7 publications

Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees

Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees

The Current Status of EMG Signals on Kinematics Needed for Precise Online Myoelectric Control and the Development Direction

Classification of EMG signals taken from arm with hybrid CNN‐SVM architecture

Contact Info

Product

Resources

About