Smart System for Prediction of Accurate Surface Electromyography Signals Using an Artificial Neural Network

Osama Dorgham, Ibrahim Al-Mherat, Jawdat Al-Shaer, Sulieman Bani-Ahmad and Stephen Laycock
Additional contact information
Osama Dorgham: Department of Computer Information Systems, Prince Abdullah Ben Ghazi Faculty of Information Technology, AL-Balqa Applied University, Al-Salt 19117, Jordan
Ibrahim Al-Mherat: Department of Computer Information Systems, Prince Abdullah Ben Ghazi Faculty of Information Technology, AL-Balqa Applied University, Al-Salt 19117, Jordan
Jawdat Al-Shaer: Department of Computer Information Systems, Prince Abdullah Ben Ghazi Faculty of Information Technology, AL-Balqa Applied University, Al-Salt 19117, Jordan
Sulieman Bani-Ahmad: Department of Computer Information Systems, Prince Abdullah Ben Ghazi Faculty of Information Technology, AL-Balqa Applied University, Al-Salt 19117, Jordan
Stephen Laycock: School of Computing Sciences, University of East Anglia, Norwich Research Park, Norwich NR4 7TJ, UK

Future Internet, 2019, vol. 11, issue 1, 1-20

Abstract: Bioelectric signals are used to measure electrical potential, but there are different types of signals. The electromyography (EMG) is a type of bioelectric signal used to monitor and recode the electrical activity of the muscles. The current work aims to model and reproduce surface EMG (SEMG) signals using an artificial neural network. Such research can aid studies into life enhancement for those suffering from damage or disease affecting their nervous system. The SEMG signal is collected from the surface above the bicep muscle through dynamic (concentric and eccentric) contraction with various loads. In this paper, we use time domain features to analyze the relationship between the amplitude of SEMG signals and the load. We extract some features (e.g., mean absolute value, root mean square, variance and standard deviation) from the collected SEMG signals to estimate the bicep’ muscle force for the various loads. Further, we use the R-squared value to depict the correlation between the SEMG amplitude and the muscle loads by linear fitting. The best performance the ANN model with 60 hidden neurons for three loads used (3 kg, 5 kg and 7 kg) has given a mean square error of 1.145, 1.3659 and 1.4238, respectively. The R-squared observed are 0.9993, 0.99999 and 0.99999 for predicting (reproduction step) of smooth SEMG signals.

Keywords: smart system; surface electromyography; modeling nerve signals; forearm human muscles; artificial neural network (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2019
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/11/1/25/pdf (application/pdf)
https://www.mdpi.com/1999-5903/11/1/25/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:11:y:2019:i:1:p:25-:d:199544

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().