Change search
Refine search result
1 - 1 of 1
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Ahlberg, Johan
    KTH, School of Technology and Health (STH).
    Real life analysis of myoelectric pattern recognition using continuous monitoring2016Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The use of non-invasive signal acquisition methods is today the standard for testing pattern recognition algorithms in prosthetic control. Such research had shown consecutively high performance on both prerecorded and real time data, yet when tested in real life they deteriorate.

    To investigate why, the author who is a congenital amputee, wore a prosthetic system utilizing pattern recognition control on a daily basis for a five-day period. The system generated one new classification every 50 ms and movement execution was made continuously; for classifying open/close; and by winning a majority vote; for classifying side grip, fine grip and pointer. System data was continuously collected and errors were registered through both a manual and an automatic log system.

    Calculations on extracted data show that grip classifications had an individual accuracy of 47%- 70% while open/close got 95%/98%, but if classified according to a majority vote, grips increased their accuracy to above 90% while open/close dropped to 80%. The conclusion was that majority vote might help complex classifications, like fine grips, while simpler proportional movements is exacerbated by majority voting. Major error sources were identified as signal similarities, electrode displacements and socket design.

    After the daily monitoring ended the systems functionality was tested using the "Assessment of Capacity for Myoelectric Control". The ACMC results showed that the system has similar functionality to commercial threshold control and thus is a possible viable option for both acquired and congenital amputees.

1 - 1 of 1
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf