FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2522062950> ?p ?o ?g. }

• W2522062950 endingPage "1758" @default.
• W2522062950 startingPage "1749" @default.
• W2522062950 abstract "To provide constraints on their inversion, ocean sound speed profiles (SSPs) often are modeled using empirical orthogonal functions (EOFs). However, this regularization, which uses the leading order EOFs with a minimum-energy constraint on their coefficients, often yields low resolution SSP estimates. In this paper, it is shown that dictionary learning, a form of unsupervised machine learning, can improve SSP resolution by generating a dictionary of shape functions for sparse processing (e.g. compressive sensing) that optimally compress SSPs; both minimizing the reconstruction error and the number of coefficients. These learned dictionaries (LDs) are not constrained to be orthogonal and thus, fit the given signals such that each signal example is approximated using few LD entries. Here, LDs describing SSP observations from the HF-97 experiment and the South China Sea are generated using the K-SVD algorithm. These LDs better explain SSP variability and require fewer coefficients than EOFs, describing much of the variability with one coefficient. Thus, LDs improve the resolution of SSP estimates with negligible computational burden." @default.
• W2522062950 created "2016-09-30" @default.
• W2522062950 creator A5004718675 @default.
• W2522062950 creator A5018064114 @default.
• W2522062950 date "2017-03-01" @default.
• W2522062950 modified "2023-10-02" @default.
• W2522062950 title "Dictionary learning of sound speed profiles" @default.
• W2522062950 cites W104847522 @default.
• W2522062950 cites W1634005169 @default.
• W2522062950 cites W1890834058 @default.
• W2522062950 cites W2006162047 @default.
• W2522062950 cites W2012617211 @default.
• W2522062950 cites W2016572604 @default.
• W2522062950 cites W2022831624 @default.
• W2522062950 cites W2023630749 @default.
• W2522062950 cites W2024523255 @default.
• W2522062950 cites W2034683677 @default.
• W2522062950 cites W2035801177 @default.
• W2522062950 cites W2041941664 @default.
• W2522062950 cites W2063215935 @default.
• W2522062950 cites W2078406391 @default.
• W2522062950 cites W2085068691 @default.
• W2522062950 cites W2085842701 @default.
• W2522062950 cites W2090597107 @default.
• W2522062950 cites W2090980244 @default.
• W2522062950 cites W2109100930 @default.
• W2522062950 cites W2109934484 @default.
• W2522062950 cites W2117635967 @default.
• W2522062950 cites W2128659236 @default.
• W2522062950 cites W2160380733 @default.
• W2522062950 cites W2160547390 @default.
• W2522062950 cites W2163398148 @default.
• W2522062950 cites W2170023599 @default.
• W2522062950 cites W2315214198 @default.
• W2522062950 cites W2323753194 @default.
• W2522062950 cites W2337432275 @default.
• W2522062950 cites W2427993098 @default.
• W2522062950 cites W2558460331 @default.
• W2522062950 cites W2787894218 @default.
• W2522062950 cites W3104217244 @default.
• W2522062950 cites W4235713725 @default.
• W2522062950 cites W4241068368 @default.
• W2522062950 doi "https://doi.org/10.1121/1.4977926" @default.
• W2522062950 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28372126" @default.
• W2522062950 hasPublicationYear "2017" @default.
• W2522062950 type Work @default.
• W2522062950 sameAs 2522062950 @default.
• W2522062950 citedByCount "30" @default.
• W2522062950 countsByYear W25220629502018 @default.
• W2522062950 countsByYear W25220629502019 @default.
• W2522062950 countsByYear W25220629502020 @default.
• W2522062950 countsByYear W25220629502021 @default.
• W2522062950 countsByYear W25220629502022 @default.
• W2522062950 countsByYear W25220629502023 @default.
• W2522062950 crossrefType "journal-article" @default.
• W2522062950 hasAuthorship W2522062950A5004718675 @default.
• W2522062950 hasAuthorship W2522062950A5018064114 @default.
• W2522062950 hasBestOaLocation W25220629502 @default.
• W2522062950 hasConcept C109007969 @default.
• W2522062950 hasConcept C11413529 @default.
• W2522062950 hasConcept C119857082 @default.
• W2522062950 hasConcept C121332964 @default.
• W2522062950 hasConcept C124066611 @default.
• W2522062950 hasConcept C124851039 @default.
• W2522062950 hasConcept C127313418 @default.
• W2522062950 hasConcept C13724139 @default.
• W2522062950 hasConcept C151730666 @default.
• W2522062950 hasConcept C153180895 @default.
• W2522062950 hasConcept C154945302 @default.
• W2522062950 hasConcept C1893757 @default.
• W2522062950 hasConcept C200351514 @default.
• W2522062950 hasConcept C22789450 @default.
• W2522062950 hasConcept C24890656 @default.
• W2522062950 hasConcept C2524010 @default.
• W2522062950 hasConcept C2776036281 @default.
• W2522062950 hasConcept C2776135515 @default.
• W2522062950 hasConcept C2988886741 @default.
• W2522062950 hasConcept C33923547 @default.
• W2522062950 hasConcept C41008148 @default.
• W2522062950 hasConceptScore W2522062950C109007969 @default.
• W2522062950 hasConceptScore W2522062950C11413529 @default.
• W2522062950 hasConceptScore W2522062950C119857082 @default.
• W2522062950 hasConceptScore W2522062950C121332964 @default.
• W2522062950 hasConceptScore W2522062950C124066611 @default.
• W2522062950 hasConceptScore W2522062950C124851039 @default.
• W2522062950 hasConceptScore W2522062950C127313418 @default.
• W2522062950 hasConceptScore W2522062950C13724139 @default.
• W2522062950 hasConceptScore W2522062950C151730666 @default.
• W2522062950 hasConceptScore W2522062950C153180895 @default.
• W2522062950 hasConceptScore W2522062950C154945302 @default.
• W2522062950 hasConceptScore W2522062950C1893757 @default.
• W2522062950 hasConceptScore W2522062950C200351514 @default.
• W2522062950 hasConceptScore W2522062950C22789450 @default.
• W2522062950 hasConceptScore W2522062950C24890656 @default.
• W2522062950 hasConceptScore W2522062950C2524010 @default.
• W2522062950 hasConceptScore W2522062950C2776036281 @default.
• W2522062950 hasConceptScore W2522062950C2776135515 @default.
• W2522062950 hasConceptScore W2522062950C2988886741 @default.

• next