Cost-effective system for the classification of muscular intent using surface electromyography and artificial neural networks

Anmol Khanna; Senthil Arumugam Muthukumaraswamy

doi:10.1109/ICECA.2017.8212835

Cost-effective system for the classification of muscular intent using surface electromyography and artificial neural networks

Anmol Khanna, Senthil Arumugam Muthukumaraswamy

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

This paper presents the implementation of a system to classify muscular intent. A neural network is used for this purpose. After skin preparation, feature extraction, network training and real-time testing, an average overall classification accuracy of 93.3% over three possible gestures was obtained. Ultimately, the results obtained speak to the suitability of an Arduino-based system for the acquisition and decoding of muscular intent. This result is indicative of the potential of the Arduino microcontroller in this application, to provide effective performance at a far lower price-point than its competition.

Original language	English
Title of host publication	2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)
Publisher	IEEE
Pages	366-371
Number of pages	6
ISBN (Electronic)	9781509056866
ISBN (Print)	9781509056859
DOIs	https://doi.org/10.1109/ICECA.2017.8212835
Publication status	Published - 18 Dec 2017

Keywords

Arduino
Cost-Effective
Electromyography
Muscular Intent
Neural Network
Orthosis
Prosthesis

ASJC Scopus subject areas

Computer Networks and Communications
Aerospace Engineering
Electrical and Electronic Engineering
Instrumentation
Safety, Risk, Reliability and Quality

Access to Document

10.1109/ICECA.2017.8212835

Cite this

@inproceedings{37a54be5b246486f8b70cbe37677127f,

title = "Cost-effective system for the classification of muscular intent using surface electromyography and artificial neural networks",

abstract = "This paper presents the implementation of a system to classify muscular intent. A neural network is used for this purpose. After skin preparation, feature extraction, network training and real-time testing, an average overall classification accuracy of 93.3% over three possible gestures was obtained. Ultimately, the results obtained speak to the suitability of an Arduino-based system for the acquisition and decoding of muscular intent. This result is indicative of the potential of the Arduino microcontroller in this application, to provide effective performance at a far lower price-point than its competition.",

keywords = "Arduino, Cost-Effective, Electromyography, Muscular Intent, Neural Network, Orthosis, Prosthesis",

author = "Anmol Khanna and Muthukumaraswamy, {Senthil Arumugam}",

year = "2017",

month = dec,

day = "18",

doi = "10.1109/ICECA.2017.8212835",

language = "English",

isbn = "9781509056859",

pages = "366--371",

booktitle = "2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)",

publisher = "IEEE",

address = "United States",

}

Cost-effective system for the classification of muscular intent using surface electromyography and artificial neural networks. / Khanna, Anmol; Muthukumaraswamy, Senthil Arumugam.
2017 International conference of Electronics, Communication and Aerospace Technology (ICECA). IEEE, 2017. p. 366-371.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Cost-effective system for the classification of muscular intent using surface electromyography and artificial neural networks

AU - Khanna, Anmol

AU - Muthukumaraswamy, Senthil Arumugam

PY - 2017/12/18

Y1 - 2017/12/18

N2 - This paper presents the implementation of a system to classify muscular intent. A neural network is used for this purpose. After skin preparation, feature extraction, network training and real-time testing, an average overall classification accuracy of 93.3% over three possible gestures was obtained. Ultimately, the results obtained speak to the suitability of an Arduino-based system for the acquisition and decoding of muscular intent. This result is indicative of the potential of the Arduino microcontroller in this application, to provide effective performance at a far lower price-point than its competition.

AB - This paper presents the implementation of a system to classify muscular intent. A neural network is used for this purpose. After skin preparation, feature extraction, network training and real-time testing, an average overall classification accuracy of 93.3% over three possible gestures was obtained. Ultimately, the results obtained speak to the suitability of an Arduino-based system for the acquisition and decoding of muscular intent. This result is indicative of the potential of the Arduino microcontroller in this application, to provide effective performance at a far lower price-point than its competition.

KW - Arduino

KW - Cost-Effective

KW - Electromyography

KW - Muscular Intent

KW - Neural Network

KW - Orthosis

KW - Prosthesis

UR - http://www.scopus.com/inward/record.url?scp=85047096414&partnerID=8YFLogxK

U2 - 10.1109/ICECA.2017.8212835

DO - 10.1109/ICECA.2017.8212835

M3 - Conference contribution

AN - SCOPUS:85047096414

SN - 9781509056859

SP - 366

EP - 371

BT - 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)

PB - IEEE

ER -

Cost-effective system for the classification of muscular intent using surface electromyography and artificial neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this