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
Automatic Sleep Scoring Using Keras
KTH, School of Engineering Sciences (SCI).
KTH, School of Engineering Sciences (SCI).
2018 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Automatisk sömnklassifiering med hjälp av Keras (Swedish)
Abstract [en]

Sleep scoring is a diagnosis tool used for medical research. Using electroencefalography (EEG) a researcher observes the electrical activity in the brain and classifies the EEG into different stages. The goal of this project is to develop a tool for automatic classification of sleep data from rodents, one of the most common test subjects in modern medical research. EEG data from AstraZeneca is used to train a neural network, developed with Keras. Some augmentation of the data is done to increase the accuracy. The data is classified into different sleep stages with 91% accuracy.

Abstract [sv]

Sömnklassifiering är ett verktyg för att diagnostistera sömn. Det används vid medicinsk forskning. Genom elektroencefalografi (EEG) observerar en forskare den elektriska aktiviteten i hjärnan och klassifierar sen EEG:n i olika stadier, i detta fall vaken, REM och NREM. Projektets mål är att utveckla ett verktyg för automatisk klassifiering av sömndata från råttor, ett av de vanligaste försöksdjuren i modern medicinsk forskning. EEG-data från Astra Zeneca används för att träna ett neural nätverk som utvecklats i Keras. Viss augmentering av datan görs för att öka träffsäkerheten. Datan klassifieras i de tre stadierna med 91% träffsäkerhet.

 

Place, publisher, year, edition, pages
2018. , p. 12
Series
TRITA-SCI-GRU ; 2018-092
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-230905OAI: oai:DiVA.org:kth-230905DiVA, id: diva2:1220116
Supervisors
Examiners
Available from: 2018-06-18 Created: 2018-06-18 Last updated: 2018-11-30Bibliographically approved

Open Access in DiVA

fulltext(699 kB)21 downloads
File information
File name FULLTEXT01.pdfFile size 699 kBChecksum SHA-512
7baa4a1e0ee775225c62ab5c789496f7e3fdadeaba9b25738da9e98326910ff22b6c0da0b9bdd0263f02e7adc5d79a1cdd34dff2a9965efca44e7dcc27d10682
Type fulltextMimetype application/pdf

By organisation
School of Engineering Sciences (SCI)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 21 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: 86 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