Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Classification of motor commands using a modified self-organising feature map.

Sebelius, Fredrik LU orcid ; Eriksson, L ; Holmberg, Hans LU ; Levinsson, Anders LU ; Lundborg, Göran LU ; Danielsen, Nils LU ; Schouenborg, Jens LU ; Balkenius, Christian LU orcid ; Laurell, Thomas LU and Montelius, Lars LU (2005) In Medical Engineering & Physics 27(5). p.403-413
Abstract
In this paper, a control system for an advanced prosthesis is proposed and has been investigated in two different biological systems: (1) the spinal withdrawal reflex system of a rat and (2) voluntary movements in two human males: one normal subject and one subject with a traumatic hand amputation. The small-animal system was used as a model system to test different processing methods for the prosthetic control system. The best methods were then validated in the human set-up. The recorded EMGs were classified using different ANN algorithms, and it was found that a modified self-organising feature map (SOFM) composed of a combination of a Kohonen network and the conscience mechanism algorithm (KNC) was superior in performance to the... (More)
In this paper, a control system for an advanced prosthesis is proposed and has been investigated in two different biological systems: (1) the spinal withdrawal reflex system of a rat and (2) voluntary movements in two human males: one normal subject and one subject with a traumatic hand amputation. The small-animal system was used as a model system to test different processing methods for the prosthetic control system. The best methods were then validated in the human set-up. The recorded EMGs were classified using different ANN algorithms, and it was found that a modified self-organising feature map (SOFM) composed of a combination of a Kohonen network and the conscience mechanism algorithm (KNC) was superior in performance to the reference networks (e.g. multi-layer perceptrons) as regards training time, low memory consumption, and simplicity in finding optimal training parameters and architecture. The KNC network classified both experimental set-ups with high accuracy, including five movements for the animal set-up and seven for the human set-up. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Medical Engineering & Physics
volume
27
issue
5
pages
403 - 413
publisher
Elsevier
external identifiers
  • pmid:15863349
  • wos:000229899300006
  • scopus:20944442083
  • pmid:15863349
ISSN
1873-4030
DOI
10.1016/j.medengphy.2004.09.008
language
English
LU publication?
yes
additional info
The information about affiliations in this record was updated in December 2015. The record was previously connected to the following departments: Reconstructive Surgery (013240300), Ophthalmology (Lund) (013043000), Neural Interfaces (013212003), Hand Surgery Research Group (013241910), Medical Radiology Unit (013241410), Neurophysiology (013212004), Cognitive Science (015001004), Biomedical Engineering (011200011), Preventive medicine (ceased) (LUR000017), Solid State Physics (011013006), Neuronano Research Center (NRC) (013210020)
id
4a4ed4db-03c3-482a-9af1-82ed261cb0e2 (old id 138238)
alternative location
http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=15863349&dopt=Abstract
date added to LUP
2016-04-04 09:26:34
date last changed
2022-02-13 17:16:21
@article{4a4ed4db-03c3-482a-9af1-82ed261cb0e2,
  abstract     = {{In this paper, a control system for an advanced prosthesis is proposed and has been investigated in two different biological systems: (1) the spinal withdrawal reflex system of a rat and (2) voluntary movements in two human males: one normal subject and one subject with a traumatic hand amputation. The small-animal system was used as a model system to test different processing methods for the prosthetic control system. The best methods were then validated in the human set-up. The recorded EMGs were classified using different ANN algorithms, and it was found that a modified self-organising feature map (SOFM) composed of a combination of a Kohonen network and the conscience mechanism algorithm (KNC) was superior in performance to the reference networks (e.g. multi-layer perceptrons) as regards training time, low memory consumption, and simplicity in finding optimal training parameters and architecture. The KNC network classified both experimental set-ups with high accuracy, including five movements for the animal set-up and seven for the human set-up.}},
  author       = {{Sebelius, Fredrik and Eriksson, L and Holmberg, Hans and Levinsson, Anders and Lundborg, Göran and Danielsen, Nils and Schouenborg, Jens and Balkenius, Christian and Laurell, Thomas and Montelius, Lars}},
  issn         = {{1873-4030}},
  language     = {{eng}},
  number       = {{5}},
  pages        = {{403--413}},
  publisher    = {{Elsevier}},
  series       = {{Medical Engineering & Physics}},
  title        = {{Classification of motor commands using a modified self-organising feature map.}},
  url          = {{http://dx.doi.org/10.1016/j.medengphy.2004.09.008}},
  doi          = {{10.1016/j.medengphy.2004.09.008}},
  volume       = {{27}},
  year         = {{2005}},
}