A Brief Review of Strategies Used for EMG Signal Classification

Inam, Shehla; Harmain, Sana Al; Shafique, Shehzaib; Afzal, Mafia; Rabail, Arfa; Amin, Faisal; Waqar, Muhammad

doi:10.1109/icai52203.2021.9445257

Cited by 15 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In myoelectric control, mostly LDA has been used for real time application due to it simple structure and linearity property and hence with minimal delay time. But several studies have shown that LDA with simple structures have shown comparatively poor performance as compare to complexity of the non-linear SVM classifier which has shown state of the art performance for different finger movements [16], [17]. Delay should not be more than 300 ms for myoelectric control [18] and here we have shown that instead of linear classifiers, nonlinear SVM could also be implemented with acceptable delay time.…”

Section: Introductionmentioning

confidence: 71%

SVM-based Real-Time Classification of Prosthetic Fingers using Myo Armband-acquired Electromyography Data

Akmal

Qureshi

Amin

et al. 2021

2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)

Self Cite

View full text Add to dashboard Cite

In this work we applied real-time classification of prosthetic fingers movements using surface electromyography (sEMG) data. We employed support vector machine (SVM) for classification of fingers movements. SVM has some benefits over other classification techniques e.g. 1) it avoids overfitting, 2) handles nonlinear data efficiently and 3) it is stable. SVM is employed on Raspberry pi which is a low-cost, credit-card sized computer with high processing power. Moreover, it supports Python which makes it easy to build projects and it has multiple interfaces available. In this paper, our aim is to perform classification of prosthetic hand relative to human fingers. To assess the performance of our framework we tested it on ten healthy subjects. Our framework was able to achieve mean classification accuracy of 78%.

show abstract

Section: Introductionmentioning

confidence: 71%

SVM-based Real-Time Classification of Prosthetic Fingers using Myo Armband-acquired Electromyography Data

Akmal

Qureshi

Amin

et al. 2021

2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The learning models of this study were selected based on the original classification case study of NinaPro dataset published in [ 24 , 29 ]. Moreover, the most common classification models surveyed in [ 28 , 30 ] have been considered in this work. Except for CNN, all the other algorithms are trained on extracted features.…”

Section: Methodsmentioning

confidence: 99%

A Systematic Study on Electromyography-Based Hand Gesture Recognition for Assistive Robots Using Deep Learning and Machine Learning Models

Gopal

Gesta

Mohebbi

2022

Sensors

View full text Add to dashboard Cite

Upper limb amputation severely affects the quality of life and the activities of daily living of a person. In the last decade, many robotic hand prostheses have been developed which are controlled by using various sensing technologies such as artificial vision and tactile and surface electromyography (sEMG). If controlled properly, these prostheses can significantly improve the daily life of hand amputees by providing them with more autonomy in physical activities. However, despite the advancements in sensing technologies, as well as excellent mechanical capabilities of the prosthetic devices, their control is often limited and usually requires a long time for training and adaptation of the users. The myoelectric prostheses use signals from residual stump muscles to restore the function of the lost limbs seamlessly. However, the use of the sEMG signals in robotic as a user control signal is very complicated due to the presence of noise, and the need for heavy computational power. In this article, we developed motion intention classifiers for transradial (TR) amputees based on EMG data by implementing various machine learning and deep learning models. We benchmarked the performance of these classifiers based on overall generalization across various classes and we presented a systematic study on the impact of time domain features and pre-processing parameters on the performance of the classification models. Our results showed that Ensemble learning and deep learning algorithms outperformed other classical machine learning algorithms. Investigating the trend of varying sliding window on feature-based and non-feature-based classification model revealed interesting correlation with the level of amputation. The study also covered the analysis of performance of classifiers on amputation conditions since the history of amputation and conditions are different to each amputee. These results are vital for understanding the development of machine learning-based classifiers for assistive robotic applications.

show abstract

“…Only 64, 256, and 1024 points of fast Fourier transformation (FFT), which is a method to analyze the power-related characteristics of signals from the aspect of the frequency domain, were allowed on the F1 series of the STM32 [ 39 ]. Time-frequency analysis is an important key to EMG signal feature extraction [ 40 , 41 ]. Due to the selected sampling rate and the requirement for a quick response, the FFT of 64 points was used in this study.…”

Section: Preprocessing and Feature Extractionmentioning

confidence: 99%

“…Many classification methods, such as k-nearest neighbours (k-NN) [ 26 , 28 ], linear discriminant analysis (LDA) [ 26 , 39 ], quadratic discriminant analysis (QDA) [ 28 ], support vector machine (SVM) [ 27 , 28 , 41 ], random tree (RT) [ 28 ], random forest (RF) [ 28 , 41 ], artificial neural networks (ANN) [ 26 , 38 , 41 ], Bayes classifier [ 26 , 38 ], self-organising map (SOP), and fuzzy classifiers [ 41 ], are available in the literature.…”

Section: Classificationmentioning

confidence: 99%

Portable Face‐Shielding Device Based on sEMG Considering the COVID‐19 Scenario

Lyu

Liu

Shao

et al. 2023

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Wearing a mask greatly reduced the possibility of infection during the COVID-19 pandemic. However, major inconveniences occur regarding patients with upper limb amputations, as they cannot independently wear masks. As a result, bacterial contamination is caused by medical staff touching the quilt when helping. Furthermore, this effect can occur with ordinary people due to accidental touch. This research aims to design an automatic and portable face shield assistive device based on surface electromyography (sEMG) signals. A concise face shield-wearing mechanism was built through 3D printing. A novel decision-making control method regarding a feature extraction model of 16 signal features and a Softmax classification neural network model were developed and tested on an STM32 microcontroller unit (MCU). The optimized electrode was fabricated using a carbon nanotube (CNT)/polydimethylsiloxane (PDMS). The design was further integrated and tested, showing a promising future for further implementation.

show abstract

A Brief Review of Strategies Used for EMG Signal Classification

Cited by 15 publications

References 21 publications

SVM-based Real-Time Classification of Prosthetic Fingers using Myo Armband-acquired Electromyography Data

SVM-based Real-Time Classification of Prosthetic Fingers using Myo Armband-acquired Electromyography Data

A Systematic Study on Electromyography-Based Hand Gesture Recognition for Assistive Robots Using Deep Learning and Machine Learning Models

Portable Face‐Shielding Device Based on sEMG Considering the COVID‐19 Scenario

Contact Info

Product

Resources

About