kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct 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
Classification of healthy and Parkinson’s disease state mice using whisker movements
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science.
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science.
2022 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Klassificering av morrhårsrörelser hos musmodeller med Parkinsons sjukdom och friska möss (Swedish)
Abstract [en]

Modelling diseases in mice provides a useful way of studying the disease. The motor symptoms of Parkinson’s disease (PD) can be studied by observing the whisker movements of mice with PD condition. Mice use their whiskers to gather information about their environment and guide their locomotion. In this study whisker movement data gathered from healthy and PD modelled mice were examined. Complex behaviors such as whisking, a cyclic bilateral movement of whiskers, are comprised of smaller modules called syllables. The syllables in the whisking data was identified using K-means, a clustering algorithm. Time series of these syllables were used to train an Long short-term memory (LSTM) classification model. The model was trained on the left and right hand side whiskers respectively to investigate any differences between the two sides. The results from the classification shows a slight difference in one of the clustering groups. However, no overall significant difference was observed.

Abstract [sv]

Modellering av sjukdomar i möss är ett användbart verktyg för att studera sjukdomar. De motoriska symptom som tar sig uttryck vid Parkinson’s sjukdom kan undersökas genom att studera morrhårsrörelser hos möss med Parkinson’s. Möss använder deras morrhår för att samla information om deras omgivning och hjälpa dem navigera. Tidsserier innehållandes information om morrhårsrörelser från friska möss och möss med Parkinson’s analyseras i denna studie. Komplexa rörelser, som rörelser av morrhår, är uppbyggda av mindre moduler som kallas stavelser (syllables). Dessa stavelser identifierades i datan med hjälp av maskininlärningsalgoritmen K-means, en klustringsmetod. Tidsserier av dessa stavelser användes för att träna en Long short-term memory (LSTM) klassifiseringsmodell. Modellen tränades med data från vänster och höger morrhår separat för att undersöka eventualla skillnader dem emellan. Resultaten från klassifiseringsmodellen visar på en svag skillnad mellan de två sidorna i en utav stavelsegrupperna. Inga signifikanta och övergripande skillnader observerades dock.

Place, publisher, year, edition, pages
2022. , p. 21
Series
TRITA-EECS-EX ; 2022:449
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-319525OAI: oai:DiVA.org:kth-319525DiVA, id: diva2:1700455
Subject / course
Computer Science
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2022-10-05 Created: 2022-10-01 Last updated: 2022-10-05Bibliographically approved

Open Access in DiVA

fulltext(2952 kB)147 downloads
File information
File name FULLTEXT01.pdfFile size 2952 kBChecksum SHA-512
6ded1dc62e6216c0f34dc18da0932b9d3ca77cacbb20f9b2c7c76f3c21f37e2636fb309cf566fdb3f3b58bbbf5a7371cf789b728cfb129ee79e1515fbcc0b421
Type fulltextMimetype application/pdf

By organisation
Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 147 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 309 hits
CiteExportLink to record
Permanent link

Direct 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