Simultaneous and proportional control of 2D wrist movements with myoelectric signals

J. M. Hahne, H. Rehbaum, F. Biessmann, F. C. Meinecke, Klaus Muller, N. Jiang, D. Farina, L. C. Parra

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Citations (Scopus)

Abstract

Previous approaches for extracting real-time proportional control information simultaneously for multiple degree of Freedom(DoF) from the electromyogram (EMG) often used non-linear methods such as the multilayer perceptron (MLP). In this pilot study we show that robust control is also possible with conventional linear regression if EMG power measures are available for a large number of electrodes. In particular, we show that it is possible to linearize the problem with simple nonlinear transformations of band-pass power. Because of its simplicity the method scales well to high dimensions, is easily regularized when insufficient training data is available, and is particularly well suited for real-time control as well as on-line optimization.

Original languageEnglish
Title of host publicationIEEE International Workshop on Machine Learning for Signal Processing, MLSP
DOIs
Publication statusPublished - 2012 Dec 12
Event2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012 - Santander, Spain
Duration: 2012 Sep 232012 Sep 26

Other

Other2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012
CountrySpain
CitySantander
Period12/9/2312/9/26

Fingerprint

Real time control
Multilayer neural networks
Robust control
Linear regression
Electrodes

Keywords

  • Electromyography (EMG)
  • linear regression
  • myoelectric control
  • simultaneous control
  • upper limb prosthesis

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Cite this

Hahne, J. M., Rehbaum, H., Biessmann, F., Meinecke, F. C., Muller, K., Jiang, N., ... Parra, L. C. (2012). Simultaneous and proportional control of 2D wrist movements with myoelectric signals. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP [6349712] https://doi.org/10.1109/MLSP.2012.6349712

Simultaneous and proportional control of 2D wrist movements with myoelectric signals. / Hahne, J. M.; Rehbaum, H.; Biessmann, F.; Meinecke, F. C.; Muller, Klaus; Jiang, N.; Farina, D.; Parra, L. C.

IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2012. 6349712.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hahne, JM, Rehbaum, H, Biessmann, F, Meinecke, FC, Muller, K, Jiang, N, Farina, D & Parra, LC 2012, Simultaneous and proportional control of 2D wrist movements with myoelectric signals. in IEEE International Workshop on Machine Learning for Signal Processing, MLSP., 6349712, 2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012, Santander, Spain, 12/9/23. https://doi.org/10.1109/MLSP.2012.6349712
Hahne JM, Rehbaum H, Biessmann F, Meinecke FC, Muller K, Jiang N et al. Simultaneous and proportional control of 2D wrist movements with myoelectric signals. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2012. 6349712 https://doi.org/10.1109/MLSP.2012.6349712
Hahne, J. M. ; Rehbaum, H. ; Biessmann, F. ; Meinecke, F. C. ; Muller, Klaus ; Jiang, N. ; Farina, D. ; Parra, L. C. / Simultaneous and proportional control of 2D wrist movements with myoelectric signals. IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2012.
@inproceedings{3e50d044818d44198e41db358aa4c8de,
title = "Simultaneous and proportional control of 2D wrist movements with myoelectric signals",
abstract = "Previous approaches for extracting real-time proportional control information simultaneously for multiple degree of Freedom(DoF) from the electromyogram (EMG) often used non-linear methods such as the multilayer perceptron (MLP). In this pilot study we show that robust control is also possible with conventional linear regression if EMG power measures are available for a large number of electrodes. In particular, we show that it is possible to linearize the problem with simple nonlinear transformations of band-pass power. Because of its simplicity the method scales well to high dimensions, is easily regularized when insufficient training data is available, and is particularly well suited for real-time control as well as on-line optimization.",
keywords = "Electromyography (EMG), linear regression, myoelectric control, simultaneous control, upper limb prosthesis",
author = "Hahne, {J. M.} and H. Rehbaum and F. Biessmann and Meinecke, {F. C.} and Klaus Muller and N. Jiang and D. Farina and Parra, {L. C.}",
year = "2012",
month = "12",
day = "12",
doi = "10.1109/MLSP.2012.6349712",
language = "English",
isbn = "9781467310260",
booktitle = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

}

TY - GEN

T1 - Simultaneous and proportional control of 2D wrist movements with myoelectric signals

AU - Hahne, J. M.

AU - Rehbaum, H.

AU - Biessmann, F.

AU - Meinecke, F. C.

AU - Muller, Klaus

AU - Jiang, N.

AU - Farina, D.

AU - Parra, L. C.

PY - 2012/12/12

Y1 - 2012/12/12

N2 - Previous approaches for extracting real-time proportional control information simultaneously for multiple degree of Freedom(DoF) from the electromyogram (EMG) often used non-linear methods such as the multilayer perceptron (MLP). In this pilot study we show that robust control is also possible with conventional linear regression if EMG power measures are available for a large number of electrodes. In particular, we show that it is possible to linearize the problem with simple nonlinear transformations of band-pass power. Because of its simplicity the method scales well to high dimensions, is easily regularized when insufficient training data is available, and is particularly well suited for real-time control as well as on-line optimization.

AB - Previous approaches for extracting real-time proportional control information simultaneously for multiple degree of Freedom(DoF) from the electromyogram (EMG) often used non-linear methods such as the multilayer perceptron (MLP). In this pilot study we show that robust control is also possible with conventional linear regression if EMG power measures are available for a large number of electrodes. In particular, we show that it is possible to linearize the problem with simple nonlinear transformations of band-pass power. Because of its simplicity the method scales well to high dimensions, is easily regularized when insufficient training data is available, and is particularly well suited for real-time control as well as on-line optimization.

KW - Electromyography (EMG)

KW - linear regression

KW - myoelectric control

KW - simultaneous control

KW - upper limb prosthesis

UR - http://www.scopus.com/inward/record.url?scp=84870701117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870701117&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2012.6349712

DO - 10.1109/MLSP.2012.6349712

M3 - Conference contribution

AN - SCOPUS:84870701117

SN - 9781467310260

BT - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

ER -