Abstract
Myoelectric signals are regarded as the control signal for prosthetic limbs. But, the main research challenge is reliable and repeatable movement detection using electromyography. In this study, the analysis of the muscle synergy pattern has been considered as a key idea to cope with this main challenge. The main objective of this research was to provide an analytical tool to recognize six wrist movements through electromyography (EMG) based on analysis of the muscle synergy patterns. In order to design such a system‚ the synergy patterns of the wrist muscles have been extracted and utilized to identify wrist movements. Also, different decision fusion algorithms were used to increase the reliability of the synergy pattern classification. The classification performance was evaluated while no data subject was enrolled. In terms of the achieved performance, using a multi-layer perceptron (MLP) neural network as the fusion algorithm turned out to be the best combination. The classification average accuracy, obtained in an offline manner, was about 99.78 ± 0.45%. While the classification average cross-validation accuracy, obtained in an offline manner, using Bayesian fusion, and Bayesian fuzzy clustering (BFC) fusion algorithm were 99.33 ± 0.80% and 96.43 ± 1.08%, respectively.
Highlights
The electromyogram (EMG) signal represents the electrical potentials generated in the muscles during muscle contraction, which shows the important neuromuscular information [1]
Six pairs of Ag– AgCl surface bipolar electrodes were placed on the extensor digitorum, flexor pollicis longus, extensor carpi ulnaris, abductor pollicis longus, pronator teres, and supinator forearm muscles
4 Discussion In this paper, the separation of different wrist movements based on muscle synergy patterns was performed using self-organizing feature map (SOFM) and based on fusion (i.e., multi-layer perceptron (MLP), Bayesian, and Bayesian fuzzy clustering (BFC)) algorithms
Summary
The electromyogram (EMG) signal represents the electrical potentials generated in the muscles during muscle contraction, which shows the important neuromuscular information [1]. The EMG signal recorded from each surface electrode is the total potential of the motor units in the region where the electrode is positioned [2]. Due to the useful application of EMG signal in clinical diagnoses, and biomedical applications as well as rehabilitation, they are considered as one of the best resources of controlling (i.e., prostheses, robots, and human-computer interfaces), recognition of intended limb movements [1, 3]. Extensive research has been done in order to control various functions and increase the efficiency of prostheses (i.e., several degrees-of-freedom (DoF). One class of the known control approaches are based on recognizing the pattern of EMG signals elicited from the residual healthy muscles [3]. Many researchers are engaged in improving the performance of such recognition algorithms in order to improve the efficiency of prostheses. The estimation algorithms, pattern recognition and regression methods [4, 5], and their combination [6, 7] are among the topics of interest to researchers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
