Go to page
 

Bibliographic Metadata

Title
Combining two open source tools for neural computation (BioPatRec and Netlab) improves movement classification for prosthetic control / Cosima Prahm, Korbinian Eckstein, Max OrtizCatalan, Georg Dorffner, Eugenijus Kaniusas and Oskar C. Aszmann
AuthorPrahm, Cosima ; Eckstein, Korbinian ; Ortiz-Catalan, Max ; Dorffner, Georg In der Gemeinsamen Normdatei der DNB nachschlagen ; Kaniusas, Eugenijus In der Gemeinsamen Normdatei der DNB nachschlagen ; Aszmann, Oskar C.
Published in
BMC Research Notes, London, 2016,
Published2016
Edition
Published version
Description1 Online-Ressource (7 Seiten) : Diagramme
LanguageEnglish
Document typeJournal Article
Keywords (EN)Prosthetics / Upper limb amputation / Machine learning / Pattern recognition / Neural computation
ISSN1756-0500
URNurn:nbn:at:at-ubtuw:3-2556 Persistent Identifier (URN)
DOI10.1186/s13104-016-2232-y 
Restriction-Information
 The work is publicly available
Files
Combining two open source tools for neural computation (BioPatRec and Netlab) improves movement classification for prosthetic control [1.09 mb]
Links
Reference
Classification
Abstract (English)

Background

Controlling a myoelectric prosthesis for upper limbs is increasingly challenging for the user as more electrodes and joints become available. Motion classification based on pattern recognition with a multi-electrode array allows multiple joints to be controlled simultaneously. Previous pattern recognition studies are difficult to compare, because individual research groups use their own data sets. To resolve this shortcoming and to facilitate comparisons, open access data sets were analysed using components of BioPatRec and Netlab pattern recognition models.

Methods

Performances of the artificial neural networks, linear models, and training program components were compared. Evaluation took place within the BioPatRec environment, a Matlab-based open source platform that provides feature extraction, processing and motion classification algorithms for prosthetic control. The algorithms were applied to myoelectric signals for individual and simultaneous classification of movements, with the aim of finding the best performing algorithm and network model. Evaluation criteria included classification accuracy and training time.

Results

Results in both the linear and the artificial neural network models demonstrated that Netlabs implementation using scaled conjugate training algorithm reached significantly higher accuracies than BioPatRec.

Conclusions

It is concluded that the best movement classification performance would be achieved through integrating Netlab training algorithms in the BioPatRec environment so that future prosthesis training can be shortened and control made more reliable. Netlab was therefore included into the newest release of BioPatRec (v4.0).

Stats
The PDF-Document has been downloaded 31 times.
License
CC-BY-License (4.0)Creative Commons Attribution 4.0 International License