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
Designing Effective Derivative Line Filters: Utilizing convolution to extract extra information
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematics (Div.).
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Utformning av effektiva derivata-linjefilter: Användning av faltning för att extrahera extra information (English)
Abstract [en]

The ability to generate accurate approximations of derivatives holds significant importance in numerous scientific fields, including chemistry, economics and fluid mechanics. This thesis is centred around extracting hidden information in data using Smoothness-Increasing Accuracy-Conserving (SIAC) filters. The target application is in calculating derivatives in simulations of fluid flow. SIAC filters are based on convolution. Because of the properties used to construct the convolution kernel, we are able to design post-processing filters that can extract extra derivative information with high accuracy. In the past, these filters have typically had a tensor-product structure, which requires multi-dimensional filtering. Because of this, the filtering process can be very computationally expensive. The goal of this thesis is to develop one-dimensional line filters that are able to extract the derivative information more efficiently. By utilizing line filters, we aim to significantly cut the computational cost of the filtering process, while also maintaining the high accuracy.

Abstract [sv]

Att kunna generera approximeringar av derivator med hög noggrannhet har stor användning inom många vetenskapliga områden, inklusive kemi, ekonomi och strömningsmekanik. Denna uppsats är fokuserad på att extrahera dold information i data med hjälp av en specifik typ av faltningsfilter. Dessa filter kan öka kontinuitetsgraden av data utan att minska noggrannheten. Den avsedda tilläpningen för dessa filter är inom strömningsmekanik, framförallt beräkning av derivator i flöden. Tack vare egenskaperna som används för att konstruera faltningskärnan kan vi utforma efterbehandlingsfilter som kan extrahera derivatainformation med hög noggrannhet. Tidigare har dessa filter ofta haft en tensorproduktstruktur, vilket kräver flerdimensionell filtrering. På grund av detta har filtreringen ofta en hög beräkningskostnad. Målet med denna uppsats är att utveckla endimensionella linjefilter som kan extrahera derivatainformation mer effektivt. Syftet är att använda dessa linjefilter för att betydligt miska filtreringens beräkningskostnad och samtidigt behålla den höga noggrannheten.

Place, publisher, year, edition, pages
2023. , p. 85
Series
TRITA-SCI-GRU ; 2023:449
Keywords [en]
Computational Fluid Dynamics, Convolution Filters, Convolution Kernels, Derivatives, Extracting Extra Accuracy, Filtration, Post-processing, Smoothness-Increasing Accuracy-Conserving, Signal-processing, Visualization, Vorticity
Keywords [sv]
Beräkningsbaserad Strömningsdynamik, Faltningsfilter, Faltningskärnor, Derivator, Extrahering av Extra Noggrannhet, Filtrering, Efterbehandling, Kontinuitetsökande, Noggrannhetsbevarande, Signalbehandling, Visualisering, Vorticitet
National Category
Computational Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-344217OAI: oai:DiVA.org:kth-344217DiVA, id: diva2:1843151
Subject / course
Scientific Computing
Educational program
Master of Science - Applied and Computational Mathematics
Supervisors
Examiners
Available from: 2024-03-22 Created: 2024-03-08 Last updated: 2024-03-22Bibliographically approved

Open Access in DiVA

fulltext(8497 kB)234 downloads
File information
File name FULLTEXT01.pdfFile size 8497 kBChecksum SHA-512
dad97f8a5605c4ef793d583f428290e4e202d083cb771583c8221a820e83269b0370fc5eec6c0968f12f9224ad997a8e4bb5be9108ea704678274df5a4f9e61e
Type fulltextMimetype application/pdf

By organisation
Mathematics (Div.)
Computational Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 234 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: 176 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