Myoelectric or electromyogram (EMG) signals can be useful in intelligently recognizing intended limb motion of a person. This paper presents an attempt to develop a four-channel EMG signal acquisition system as part of an ongoing research in the development of an active prosthetic device. The acquired signals are used for identification and classification of six unique movements of hand and wrist, viz. hand open, hand close, wrist flexion, wrist extension, ulnar deviation and radial deviation. This information is used for actuation of prosthetic drive. The time domain features are extracted, and their dimension is reduced using principal component analysis. The reduced features are classified using two different techniques: k nearest neighbor and artificial neural networks, and the results are compared. ©2009 IEEE.

Geethanjali P

Department of Control and Automation

School of Electrical Engineering

Vellore Campus

Ray K.K

Shanmuganathan P.V.

Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Actuation of prosthetic drive using EMG signal

TENCON 2009 - 2009 IEEE Region 10 Conference

In this paper, a low-cost mechatronics platform for the design and development of robotic hands as well as a surface electromyogram (EMG) pattern recognition system is proposed. This paper also explores various EMG classification techniques using a low-cost electronics system in prosthetic hand applications. The proposed platform involves the development of a four channel EMG signal acquisition system; pattern recognition of acquired EMG signals; and development of a digital controller for a robotic hand. Four-channel surface EMG signals, acquired from ten healthy subjects for six different movements of the hand, were used to analyse pattern recognition in prosthetic hand control. Various time domain features were extracted and grouped into five ensembles to compare the influence of features in feature-selective classifiers (SLR) with widely considered non-feature-selective classifiers, such as neural networks (NN), linear discriminant analysis (LDA) and support vector machines (SVM) applied with different kernels. The results divulged that the average classification accuracy of the SVM, with a linear kernel function, outperforms other classifiers with feature ensembles, Hudgin’s feature set and auto regression (AR) coefficients. However, the slight improvement in classification accuracy of SVM incurs more processing time and memory space in the low-level controller. The Kruskal–Wallis (KW) test also shows that there is no significant difference in the classification performance of SLR with Hudgin’s feature set to that of SVM with Hudgin’s features along with AR coefficients. In addition, the KW test shows that SLR was found to be better in respect to computation time and memory space, which is vital in a low-level controller. Similar to SVM, with a linear kernel function, other non-feature selective LDA and NN classifiers also show a slight improvement in performance using twice the features but with the drawback of increased memory space requirement and time. This prototype facilitated the study of various issues of pattern recognition and identified an efficient classifier, along with a feature ensemble, in the implementation of EMG controlled prosthetic hands in a laboratory setting at low-cost. This platform may help to motivate and facilitate prosthetic hand research in developing countries. © 2016, Australasian College of Physical Scientists and Engineers in Medicine.

Australasian Physical & Engineering Sciences in Medicine

A mechatronics platform to study prosthetic hand control using EMG signals

Electromyographic (EMG) signals are abundantly used in the field of rehabilitation engineering in controlling the prosthetic device and significantly essential to find fast and accurate EMG pattern recognition system, to avoid intrusive delay. The main objective of this paper is to study the influence of Principal component analysis (PCA), a transformation technique, in pattern recognition of six hand movements using four channel surface EMG signals from ten healthy subjects. For this reason, time domain (TD) statistical as well as auto regression (AR) coefficients are extracted from the four channel EMG signals. The extracted statistical features as well as AR coefficients are transformed using PCA to 25, 50 and 75 % of corresponding original feature vector space. The classification accuracy of PCA transformed and non-PCA transformed TD statistical features as well as AR coefficients are studied with simple logistic regression (SLR), decision tree (DT) with J48 algorithm, logistic model tree (LMT), k nearest neighbor (kNN) and neural network (NN) classifiers in the identification of six different movements. The Kruskal-Wallis (KW) statistical test shows that there is a significant reduction (P\0.05) in classification accuracy with PCA transformed features compared to non-PCA transformed features. SLR with non-PCA transformed time domain (TD) statistical features performs better in accuracy and computational power compared to other features considered in this study. In addition, the motion control of three drives for six movements of the hand is implemented with SLR using TD statistical features in offline with TMSLF2407 digital signal controller (DSC). © Australasian College of Physical Scientists and Engineers in Medicine 2015.

Comparative study of PCA in classification of multichannel EMG signals

The authors in this paper propose a statistical technique for pattern recognition of electromyogram (EMG) signals along with effective feature ensemble to achieve an improved classification performance with less processing time and memory space. In this study, EMG signals from 10 healthy subjects and two transradial amputees for six motions of hand and wrist is considered for identification of the intended motion. From four channels myoelectric signals, the extracted time domain features are grouped into three ensembles to identify the effectiveness of feature ensemble in classification. The three feature ensembles obtained from multichannel continuous EMG signals are applied to the new classifiers namely simple logistic regression (SLR), J48 algorithm for decision tree (DT), logistic model tree (LMT) and feature subspace ensemble using k-nearest neighbor (kNN). Novel classifiers SLR, DT and LMT, select only the dominant features during training to develop the model for pattern recognition. This selection of features reduces the processing time as well as memory space of the controller for real-time application. The performance of SLR, DT, LMT and feature subspace ensemble using kNN classifiers are compared with other conventional classifiers, such as neural network (NN), simple kNN and linear discriminant analysis (LDA). The average classification accuracy with SLR is found to be better with feature ensemble-1 compared to the other classifiers. Also, the statistical Kruscal–Wallis test shows, the classification performance of SLR is not only better but also takes less time and memory space compared to other classifiers for classification. Also the performance of the classifier is tested in real-time with transradial amputees for actuation of drive for two intended motions with TMS320F28335eZdsp controller. The experimental results show that the SLR classifier improves the controller response in real-time.

Biomedical Engineering: Applications, Basis and Communications

STATISTICAL PATTERN RECOGNITION TECHNIQUE FOR IMPROVED REAL-TIME MYOELECTRIC SIGNAL CLASSIFICATION

The authors in this paper propose an effective and efficient pattern recognition technique from four channel electromyogram (EMG) signals for control of multifunction prosthetic hand. Time domain features such as mean absolute value, number of zero crossings, number of slope sign changes and waveform length are considered for pattern recognition. The patterns are classified using simple logistic regression (SLR) technique and decision tree (DT) using J48 algorithm. In this study six specific hand and wrist motions are identified from the EMG signals obtained from ten different able-bodied. By considering relevant dominant features for pattern recognition, the processing time as well as memory space of the SLR and DT classifiers is found to be less in comparison with neural network (NN), k-nearest neighbour model 1 (kNN-Model-1), k-nearest neighbour model 2 (kNN-Model-2) and linear discriminant analysis. The classification accuracy of SLR classifier is found to be 91 ± 1.9%. © Australasian College of Physical Scientists and Engineers in Medicine 2011.

Identification of motion from multi-channel EMG signals for control of prosthetic hand

Case Medical Research

Noraxon myoRESEARCH™ Software Gait Analysis Evaluation and Orthotic Gait Correction in Reducing Diabetic Foot Ulceration Or Subsequent Amputation in Patients With a History of a Diabetic Foot Ulceration

IEEE Transactions on Biomedical Engineering

A Real-Time EMG Pattern Recognition System Based on Linear-Nonlinear Feature Projection for a Multifunction Myoelectric Hand

IEEE Transactions on Neural Systems and Rehabilitation Engineering

A Heuristic Fuzzy Logic Approach to EMG Pattern Recognition for Multifunctional Prosthesis Control

2005 IEEE Engineering in Medicine and Biology 27th Annual Conference

A Method of Recognizing Finger Motion Using Wavelet Transform of Surface EMG Signal

IEEE/ASME Transactions on Mechatronics

An exoskeletal robot for human shoulder joint motion assist

Journal	Data powered by TypesetTENCON 2009 - 2009 IEEE Region 10 Conference
Publisher	Data powered by TypesetIEEE
Open Access	0