Optimization of Neural Network Architecture for Biomechanic Classification Tasks with Electromyogram Inputs Full Text
A. Kennedy, und R. Lewis. International Journal of Artificial Intelligence & Applications (IJAIA), 7 (5):
1-16(September 2016)
Zusammenfassung
Electromyogram signals (EMGs) contain valuable information that can be used in man-machine
interfacing between human users and myoelectric prosthetic devices. However, EMG signals are
complicated and prove difficult to analyze due to physiological noise and other issues. Computational
intelligence and machine learning techniques, such as artificial neural networks (ANNs), serve as powerful
tools for analyzing EMG signals and creating optimal myoelectric control schemes for prostheses. This
research examines the performance of four different neural network architectures (feedforward, recurrent,
counter propagation, and self organizing map) that were tasked with classifying walking speed when given
EMG inputs from 14 different leg muscles. Experiments conducted on the data set suggest that self
organizing map neural networks are capable of classifying walking speed with greater than 99% accuracy
%0 Journal Article
%1 kennedy2016optimization
%A Kennedy, Alayna
%A Lewis, Rory
%D 2016
%E David B. Bracewell, Oculus360, USA
%J International Journal of Artificial Intelligence & Applications (IJAIA)
%K Neural artificial intelligence,
%N 5
%P 1-16
%T Optimization of Neural Network Architecture for Biomechanic Classification Tasks with Electromyogram Inputs Full Text
%U http://aircconline.com/ijaia/V7N5/7516ijaia01.pdf
%V 7
%X Electromyogram signals (EMGs) contain valuable information that can be used in man-machine
interfacing between human users and myoelectric prosthetic devices. However, EMG signals are
complicated and prove difficult to analyze due to physiological noise and other issues. Computational
intelligence and machine learning techniques, such as artificial neural networks (ANNs), serve as powerful
tools for analyzing EMG signals and creating optimal myoelectric control schemes for prostheses. This
research examines the performance of four different neural network architectures (feedforward, recurrent,
counter propagation, and self organizing map) that were tasked with classifying walking speed when given
EMG inputs from 14 different leg muscles. Experiments conducted on the data set suggest that self
organizing map neural networks are capable of classifying walking speed with greater than 99% accuracy
@article{kennedy2016optimization,
abstract = {Electromyogram signals (EMGs) contain valuable information that can be used in man-machine
interfacing between human users and myoelectric prosthetic devices. However, EMG signals are
complicated and prove difficult to analyze due to physiological noise and other issues. Computational
intelligence and machine learning techniques, such as artificial neural networks (ANNs), serve as powerful
tools for analyzing EMG signals and creating optimal myoelectric control schemes for prostheses. This
research examines the performance of four different neural network architectures (feedforward, recurrent,
counter propagation, and self organizing map) that were tasked with classifying walking speed when given
EMG inputs from 14 different leg muscles. Experiments conducted on the data set suggest that self
organizing map neural networks are capable of classifying walking speed with greater than 99% accuracy},
added-at = {2016-10-26T00:46:37.000+0200},
author = {Kennedy, Alayna and Lewis, Rory},
biburl = {https://www.bibsonomy.org/bibtex/22b2a2dbafbc12b37c47fb52cc3d36483/calvin2014},
editor = {{David B. Bracewell, Oculus360}, USA},
interhash = {263304ce689ab28e2c313ef4aa7f0878},
intrahash = {2b2a2dbafbc12b37c47fb52cc3d36483},
journal = {International Journal of Artificial Intelligence & Applications (IJAIA)},
keywords = {Neural artificial intelligence,},
month = {September},
number = 5,
pages = {1-16},
timestamp = {2016-10-26T00:46:37.000+0200},
title = {Optimization of Neural Network Architecture for Biomechanic Classification Tasks with Electromyogram Inputs Full Text },
url = {http://aircconline.com/ijaia/V7N5/7516ijaia01.pdf},
volume = 7,
year = 2016
}