Matches in SemOpenAlex for { <https://semopenalex.org/work/W2261658981> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2261658981 endingPage "59" @default.
- W2261658981 startingPage "50" @default.
- W2261658981 abstract "Reconstructive discriminant analysis (RDA) is an effective dimensionality reduction method that can match well with linear regression classification (LRC). RDA seeks to find projections that can minimize the intra-class reconstruction scatter and simultaneously maximize the inter-class reconstruction scatter of samples. However, RDA needs to select the k heterogeneous nearest subspaces of each sample to construct the inter-class reconstruction scatter and it is very difficult to predefine the parameter k in practical applications. To deal with this problem, we propose a novel method called parameterless reconstructive discriminant analysis (PRDA) in this paper. Compared to traditional RDA, our proposed RDA variant cannot only fit LRC well but also has two important characteristics: (1) the performance of RDA depends on the parameter k that requires manual turning, while ours is parameter-free, and (2) it adaptively estimates the heterogeneous nearest classes for each sample to construct the inter-class reconstruction scatter. To evaluate the performance of the proposed algorithm, we test PRDA and some other state-of-the-art algorithms on some benchmark datasets such as the FERET, AR and ORL face databases. The experimental results demonstrate the effectiveness of our proposed method." @default.
- W2261658981 created "2016-06-24" @default.
- W2261658981 creator A5038362365 @default.
- W2261658981 creator A5061102708 @default.
- W2261658981 date "2016-05-01" @default.
- W2261658981 modified "2023-10-17" @default.
- W2261658981 title "Parameterless reconstructive discriminant analysis for feature extraction" @default.
- W2261658981 cites W1985809919 @default.
- W2261658981 cites W1993603321 @default.
- W2261658981 cites W2001141328 @default.
- W2261658981 cites W2002645541 @default.
- W2261658981 cites W2004144468 @default.
- W2261658981 cites W2009596443 @default.
- W2261658981 cites W2016382116 @default.
- W2261658981 cites W2028614210 @default.
- W2261658981 cites W2030095118 @default.
- W2261658981 cites W2053186076 @default.
- W2261658981 cites W2062716212 @default.
- W2261658981 cites W2097308346 @default.
- W2261658981 cites W2097486709 @default.
- W2261658981 cites W2105055468 @default.
- W2261658981 cites W2112810953 @default.
- W2261658981 cites W2117553576 @default.
- W2261658981 cites W2121647436 @default.
- W2261658981 cites W2122111042 @default.
- W2261658981 cites W2124332660 @default.
- W2261658981 cites W2129814203 @default.
- W2261658981 cites W2138451337 @default.
- W2261658981 cites W2141355396 @default.
- W2261658981 cites W2143340430 @default.
- W2261658981 cites W2153381360 @default.
- W2261658981 cites W2158281641 @default.
- W2261658981 cites W2163584563 @default.
- W2261658981 cites W2171347282 @default.
- W2261658981 cites W2171898484 @default.
- W2261658981 cites W3148981562 @default.
- W2261658981 cites W75788093 @default.
- W2261658981 doi "https://doi.org/10.1016/j.neucom.2016.01.001" @default.
- W2261658981 hasPublicationYear "2016" @default.
- W2261658981 type Work @default.
- W2261658981 sameAs 2261658981 @default.
- W2261658981 citedByCount "10" @default.
- W2261658981 countsByYear W22616589812016 @default.
- W2261658981 countsByYear W22616589812017 @default.
- W2261658981 countsByYear W22616589812018 @default.
- W2261658981 countsByYear W22616589812019 @default.
- W2261658981 countsByYear W22616589812020 @default.
- W2261658981 countsByYear W22616589812021 @default.
- W2261658981 crossrefType "journal-article" @default.
- W2261658981 hasAuthorship W2261658981A5038362365 @default.
- W2261658981 hasAuthorship W2261658981A5061102708 @default.
- W2261658981 hasConcept C153180895 @default.
- W2261658981 hasConcept C154945302 @default.
- W2261658981 hasConcept C33923547 @default.
- W2261658981 hasConcept C41008148 @default.
- W2261658981 hasConcept C52622490 @default.
- W2261658981 hasConcept C69738355 @default.
- W2261658981 hasConcept C78397625 @default.
- W2261658981 hasConceptScore W2261658981C153180895 @default.
- W2261658981 hasConceptScore W2261658981C154945302 @default.
- W2261658981 hasConceptScore W2261658981C33923547 @default.
- W2261658981 hasConceptScore W2261658981C41008148 @default.
- W2261658981 hasConceptScore W2261658981C52622490 @default.
- W2261658981 hasConceptScore W2261658981C69738355 @default.
- W2261658981 hasConceptScore W2261658981C78397625 @default.
- W2261658981 hasFunder F4320321001 @default.
- W2261658981 hasFunder F4320322769 @default.
- W2261658981 hasLocation W22616589811 @default.
- W2261658981 hasOpenAccess W2261658981 @default.
- W2261658981 hasPrimaryLocation W22616589811 @default.
- W2261658981 hasRelatedWork W1996567674 @default.
- W2261658981 hasRelatedWork W2064315893 @default.
- W2261658981 hasRelatedWork W2104912729 @default.
- W2261658981 hasRelatedWork W2122259043 @default.
- W2261658981 hasRelatedWork W2134472250 @default.
- W2261658981 hasRelatedWork W2144059113 @default.
- W2261658981 hasRelatedWork W2146076056 @default.
- W2261658981 hasRelatedWork W2387892629 @default.
- W2261658981 hasRelatedWork W2739275700 @default.
- W2261658981 hasRelatedWork W1905704307 @default.
- W2261658981 hasVolume "190" @default.
- W2261658981 isParatext "false" @default.
- W2261658981 isRetracted "false" @default.
- W2261658981 magId "2261658981" @default.
- W2261658981 workType "article" @default.