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
VASCO: Developing AI-Crawlers for ML-Blink
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The "Vanishing and Appearing Sources during a Century of Observations" (VASCO) initiative aims at finding inexplicable effects among all-sky surveys. The VASCO project is a collaboration between astronomers and information technology researchers, and incorporates explicitly a component of citizen science. In an effort to efficiently mine the historical sky survey observations, an implementation of the ML-Blink algorithm - a machine learning algorithm which uses a data-driven approach to attempt to learn what features characterize interesting candidates - is proposed and evaluated as means to recommend interesting candidates from the historical sky survey observations. The proposed ML-Blink algorithm implementation consistently achieves an area under the curve in the 0.70 range and finds 2-4 artificial anomalies out of 7 in a dataset consisting 5005 observations from the USNO-B1.0 and Pan-STARRS1 datasets.

Place, publisher, year, edition, pages
2019. , p. 51
Series
IT ; 19026
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:uu:diva-396386OAI: oai:DiVA.org:uu-396386DiVA, id: diva2:1367603
Educational program
Master Programme in Computer Science
Supervisors
Examiners
Available from: 2019-11-04 Created: 2019-11-04 Last updated: 2019-11-04Bibliographically approved

Open Access in DiVA

fulltext(3634 kB)32 downloads
File information
File name FULLTEXT01.pdfFile size 3634 kBChecksum SHA-512
1756d49ae47313638b44d8ce43229de4c4f8e938eda37d84d5f146bc540b07f752c37468f74b79019ec15422c0b7934662196491c29e6affe71179f3627c3dd7
Type fulltextMimetype application/pdf

By organisation
Department of Information Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 32 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: 255 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