Electromyography signal based hand gesture classification system using Hilbert Huang transform and deep neural networks

被引:0
作者
Vasanthi, Mary S. [1 ]
Lenin, A. Haiter [2 ]
Fouad, Yasser [3 ]
Soudagar, Manzoore Elahi M. [4 ]
机构
[1] St Xaviers Catholic Coll Engn, Dept Elect & Commun Engn, Nagercoil, Tamil Nadu, India
[2] WOLLO Univ, Kombolcha Inst Technol, Sch Mech & Chem Engn, Post Box 208, Kombolcha, Ethiopia
[3] King Saud Univ, Coll Appl Engn, Dept Appl Mech Engn, Muzahimiyah Branch, Riyadh, Saudi Arabia
[4] Lishui Univ, Fac Engn, Lishui 323000, Zhejiang, Peoples R China
关键词
Electromyography; Hilbert huang transform; Wavelet transform; Deep neural network; Learning; RECOGNITION; EMD;
D O I
10.1016/j.heliyon.2024.e32211
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
This research aims to provide the groundwork for smartly categorizing hand movements for use with prosthetic hands. The hand motions are classified using surface electromyography (sEMG) data. In reaction to a predetermined sequence of fibre activation, every single one of our muscles contracts. They could be useful in developing control protocols for bio-control systems, such human-computer interaction and upper limb prostheses. When focusing on hand gestures, data gloves and vision-based approaches are often used. The data glove technique requires tedious and unnatural user engagement, whereas the vision-based solution requires significantly more expensive sensors. This research offered a Deep Neural Network (DNN) automated hand gesticulation recognition system based on electromyography to circumvent these restrictions. This work primarily aims to augment the concert of the hand gesture recognition system via the use of an artificial classifier. To advance the recognition system's classification accuracy, this study explains how to build models of neural networks and how to use signal processing methods. By locating the Hilbert Huang Transform (HHT), one may get the essential properties of the signal. When training a DNN classifier, these characteristics are sent into it. The investigational results reveal that the suggested technique accomplishes a better categorization rate (98.5 % vs. the alternatives).
引用
收藏
页数:14
相关论文
共 41 条
[1]   Classification of EMG signals through wavelet analysis and neural networks for controlling an active hand prosthesis [J].
Arvetti, Matteo ;
Gini, Giuseppina ;
Folgheraiter, Mchele .
2007 IEEE 10TH INTERNATIONAL CONFERENCE ON REHABILITATION ROBOTICS, VOLS 1 AND 2, 2007, :531-536
[2]  
Atzori M., 2014, Pattern Recognition and Machine Learning, V29
[3]   Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands [J].
Atzori, Manfredo ;
Cognolato, Matteo ;
Mueller, Henning .
FRONTIERS IN NEUROROBOTICS, 2016, 10
[4]  
Carroll D., 2012, J. Biosens. Bioelectron., V3, P112, DOI [10.4172/2155-6210.1000e112, DOI 10.4172/2155-6210.1000E112]
[5]   Fine detection of grasp force and posture by amputees via surface electromyography [J].
Castellini, Claudio ;
Gruppioni, Emanuele ;
Davalli, Angelo ;
Sandini, Giulio .
JOURNAL OF PHYSIOLOGY-PARIS, 2009, 103 (3-5) :255-262
[6]   Digital image steganography: Survey and analysis of current methods [J].
Cheddad, Abbas ;
Condell, Joan ;
Curran, Kevin ;
Mc Kevitt, Paul .
SIGNAL PROCESSING, 2010, 90 (03) :727-752
[7]  
Choudhury A., 2015, Intelligent Applications for Heterogeneous System Modeling and Design, P261
[8]   Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning [J].
Cote-Allard, Ulysse ;
Fall, Cheikh Latyr ;
Drouin, Alexandre ;
Campeau-Lecours, Alexandre ;
Gosselin, Clement ;
Glette, Kyrre ;
Laviolette, Francois ;
Gosselin, Benoit .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2019, 27 (04) :760-771
[9]  
De Luca C.J., 2006, Electromyography
[10]  
Djebbar F., 2010, 2010 2nd International Conference on Industrial Mechatronics and Automation (ICIMA 2010), P422, DOI 10.1109/ICINDMA.2010.5538279