Linear, Kurtosis and Bayesian Filtering of EMG Drive for Abstract Myoelectric Control

Matthew Dyson; Jessica Barnes; Kianoush  Nazarpour

Linear, Kurtosis and Bayesian Filtering of EMG Drive for Abstract Myoelectric Control

Matthew Dyson, Jessica Barnes, Kianoush Nazarpour

Research output: Contribution to conference › Abstract › peer-review

Abstract / Description of output

Signal processing of sEMG is currently the most prevalent method used to control active hand prostheses. For control purposess EMG is typically transformed into a feature space representation prior to presentation to a controller or classifier. In this study we compare three signal processing techniques for myoelectric control based on low level EMG contractions: mean-absolute-value (MAV), a Bayesian estimate of the EMGs ‘neural drive’, and sequentially updated real-time Kurtosis.

Original language	English
Number of pages	1
Publication status	Published - 18 Aug 2017
Event	Myoelectric Controls Symposium 2017 - Fredericton, Canada Duration: 15 Aug 2017 → 18 Aug 2017 https://www.unb.ca/research/institutes/biomedical/mec/about.html

Conference

Conference	Myoelectric Controls Symposium 2017
Abbreviated title	MEC 2017
Country/Territory	Canada
City	Fredericton
Period	15/08/17 → 18/08/17
Internet address	https://www.unb.ca/research/institutes/biomedical/mec/about.html

Access to Document

https://www.unb.ca/research/institutes/biomedical/mec/_resources/docs/MEC17-papers/dyson-linear-kurtosis.pdfLicence: All Rights Reserved

Cite this

@conference{cbc1ed3036c0464c99e5c5e89f6a8fb4,

title = "Linear, Kurtosis and Bayesian Filtering of EMG Drive for Abstract Myoelectric Control",

abstract = "Signal processing of sEMG is currently the most prevalent method used to control active hand prostheses. For control purposess EMG is typically transformed into a feature space representation prior to presentation to a controller or classifier. In this study we compare three signal processing techniques for myoelectric control based on low level EMG contractions: mean-absolute-value (MAV), a Bayesian estimate of the EMGs {\textquoteleft}neural drive{\textquoteright}, and sequentially updated real-time Kurtosis.",

author = "Matthew Dyson and Jessica Barnes and Kianoush Nazarpour",

year = "2017",

month = aug,

day = "18",

language = "English",

note = "Myoelectric Controls Symposium 2017, MEC 2017 ; Conference date: 15-08-2017 Through 18-08-2017",

url = "https://www.unb.ca/research/institutes/biomedical/mec/about.html",

}

TY - CONF

T1 - Linear, Kurtosis and Bayesian Filtering of EMG Drive for Abstract Myoelectric Control

AU - Dyson, Matthew

AU - Barnes, Jessica

AU - Nazarpour, Kianoush

PY - 2017/8/18

Y1 - 2017/8/18

N2 - Signal processing of sEMG is currently the most prevalent method used to control active hand prostheses. For control purposess EMG is typically transformed into a feature space representation prior to presentation to a controller or classifier. In this study we compare three signal processing techniques for myoelectric control based on low level EMG contractions: mean-absolute-value (MAV), a Bayesian estimate of the EMGs ‘neural drive’, and sequentially updated real-time Kurtosis.

AB - Signal processing of sEMG is currently the most prevalent method used to control active hand prostheses. For control purposess EMG is typically transformed into a feature space representation prior to presentation to a controller or classifier. In this study we compare three signal processing techniques for myoelectric control based on low level EMG contractions: mean-absolute-value (MAV), a Bayesian estimate of the EMGs ‘neural drive’, and sequentially updated real-time Kurtosis.

M3 - Abstract

T2 - Myoelectric Controls Symposium 2017

Y2 - 15 August 2017 through 18 August 2017

ER -

Linear, Kurtosis and Bayesian Filtering of EMG Drive for Abstract Myoelectric Control

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this