EMG Signal Classification Using Reflection Coefficients and Extreme Value Machine

Azhiri, Reza Bagherian; Esmaeili, Mohammad; Jafarzadeh, Mohsen; Nourani, Mehrdad

doi:10.48550/arxiv.2106.10561

Cited by 2 publications

(2 citation statements)

References 31 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For classification, the authors utilized support vector machine (SVM) as classifier. Azhiri et al [4] extracted the same features of [3], but their classifier was extreme value machine (EVM), and improved the accuracy. Esa et al [5] used Hudgins features, root mean square (RMS) and finally combination of all these features, and a SVM classifier.…”

Section: Introductionmentioning

confidence: 99%

EMG-Based Feature Extraction and Classification for Prosthetic Hand Control

Azhiri¹,

Esmaeili²,

Nourani³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

In recent years, real-time control of prosthetic hands has gained a great deal of attention. In particular, real-time analysis of Electromyography (EMG) signals has several challenges to achieve an acceptable accuracy and execution delay. In this paper, we address some of these challenges by improving the accuracy in a shorter signal length. We first introduce a set of new feature extraction functions applying on each level of wavelet decomposition. Then, we propose a postprocessing approach to process the neural network outputs. The experimental results illustrate that the proposed method enhances the accuracy of real-time classification of EMG signals up to 95.5% for 800 msec signal length. The proposed postprocessing method achieves higher consistency compared with conventional majority voting and Bayesian fusion methods.

show abstract

Section: Introductionmentioning

confidence: 99%

EMG-Based Feature Extraction and Classification for Prosthetic Hand Control

Azhiri¹,

Esmaeili²,

Nourani³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Reference [11] performed spectral analysis on EMG signals to extract reflection coefficients as the features and then implemented SVM as a classifier to get 89% accuracy. Azhiri et al [15] has used the same features but implemented EVM and increased the accuracy to 91%. Authors in [7] extracted fractional fast Fourier transform (FrFT) as their features, and then KNN was applied as a classifier to achieve the accuracy of 98.12%.…”

Section: Introductionmentioning

confidence: 99%

Real-Time EMG Signal Classification via Recurrent Neural Networks

Azhiri¹,

Esmaeili²,

Nourani³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Real-time classification of Electromyography signals is the most challenging part of controlling a prosthetic hand. Achieving a high classification accuracy of EMG signals in a short delay time is still challenging. Recurrent neural networks (RNNs) are artificial neural network architectures that are appropriate for sequential data such as EMG. In this paper, after extracting features from a hybrid time-frequency domain (discrete Wavelet transform), we utilize a set of recurrent neural network-based architectures to increase the classification accuracy and reduce the prediction delay time. The performances of these architectures are compared and in general outperform other state-of-the-art methods by achieving 96% classification accuracy in 600 msec.

show abstract

EMG Signal Classification Using Reflection Coefficients and Extreme Value Machine

Cited by 2 publications

References 31 publications

EMG-Based Feature Extraction and Classification for Prosthetic Hand Control

EMG-Based Feature Extraction and Classification for Prosthetic Hand Control

Real-Time EMG Signal Classification via Recurrent Neural Networks

Contact Info

Product

Resources

About