Matches in SemOpenAlex for { <https://semopenalex.org/work/W2105055468> ?p ?o ?g. }
- W2105055468 endingPage "165" @default.
- W2105055468 startingPage "157" @default.
- W2105055468 abstract "In pattern recognition, feature extraction techniques are widely employed to reduce the dimensionality of data and to enhance the discriminatory information. Principal component analysis (PCA) and linear discriminant analysis (LDA) are the two most popular linear dimensionality reduction methods. However, PCA is not very effective for the extraction of the most discriminant features, and LDA is not stable due to the small sample size problem. In this paper, we propose some new (linear and nonlinear) feature extractors based on maximum margin criterion (MMC). Geometrically, feature extractors based on MMC maximize the (average) margin between classes after dimensionality reduction. It is shown that MMC can represent class separability better than PCA. As a connection to LDA, we may also derive LDA from MMC by incorporating some constraints. By using some other constraints, we establish a new linear feature extractor that does not suffer from the small sample size problem, which is known to cause serious stability problems for LDA. The kernelized (nonlinear) counterpart of this linear feature extractor is also established in the paper. Our extensive experiments demonstrate that the new feature extractors are effective, stable, and efficient." @default.
- W2105055468 created "2016-06-24" @default.
- W2105055468 creator A5034035432 @default.
- W2105055468 creator A5050209085 @default.
- W2105055468 creator A5055875299 @default.
- W2105055468 date "2006-01-01" @default.
- W2105055468 modified "2023-10-06" @default.
- W2105055468 title "Efficient and Robust Feature Extraction by Maximum Margin Criterion" @default.
- W2105055468 cites W1727290854 @default.
- W2105055468 cites W1983772724 @default.
- W2105055468 cites W1985809919 @default.
- W2105055468 cites W2001619934 @default.
- W2105055468 cites W2002645541 @default.
- W2105055468 cites W2051885135 @default.
- W2105055468 cites W2075980530 @default.
- W2105055468 cites W2088851040 @default.
- W2105055468 cites W2088900896 @default.
- W2105055468 cites W2089322632 @default.
- W2105055468 cites W2103560185 @default.
- W2105055468 cites W2107542203 @default.
- W2105055468 cites W2109363337 @default.
- W2105055468 cites W2121647436 @default.
- W2105055468 cites W2140095548 @default.
- W2105055468 cites W2146403040 @default.
- W2105055468 cites W2150796457 @default.
- W2105055468 cites W2911964244 @default.
- W2105055468 cites W4233372644 @default.
- W2105055468 cites W4237171445 @default.
- W2105055468 cites W4238240379 @default.
- W2105055468 cites W4292023222 @default.
- W2105055468 cites W7299809 @default.
- W2105055468 doi "https://doi.org/10.1109/tnn.2005.860852" @default.
- W2105055468 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/16526484" @default.
- W2105055468 hasPublicationYear "2006" @default.
- W2105055468 type Work @default.
- W2105055468 sameAs 2105055468 @default.
- W2105055468 citedByCount "732" @default.
- W2105055468 countsByYear W21050554682012 @default.
- W2105055468 countsByYear W21050554682013 @default.
- W2105055468 countsByYear W21050554682014 @default.
- W2105055468 countsByYear W21050554682015 @default.
- W2105055468 countsByYear W21050554682016 @default.
- W2105055468 countsByYear W21050554682017 @default.
- W2105055468 countsByYear W21050554682018 @default.
- W2105055468 countsByYear W21050554682019 @default.
- W2105055468 countsByYear W21050554682020 @default.
- W2105055468 countsByYear W21050554682021 @default.
- W2105055468 countsByYear W21050554682022 @default.
- W2105055468 countsByYear W21050554682023 @default.
- W2105055468 crossrefType "journal-article" @default.
- W2105055468 hasAuthorship W2105055468A5034035432 @default.
- W2105055468 hasAuthorship W2105055468A5050209085 @default.
- W2105055468 hasAuthorship W2105055468A5055875299 @default.
- W2105055468 hasBestOaLocation W21050554682 @default.
- W2105055468 hasConcept C111030470 @default.
- W2105055468 hasConcept C119857082 @default.
- W2105055468 hasConcept C138885662 @default.
- W2105055468 hasConcept C153180895 @default.
- W2105055468 hasConcept C154945302 @default.
- W2105055468 hasConcept C181367576 @default.
- W2105055468 hasConcept C27438332 @default.
- W2105055468 hasConcept C2776401178 @default.
- W2105055468 hasConcept C31510193 @default.
- W2105055468 hasConcept C33923547 @default.
- W2105055468 hasConcept C41008148 @default.
- W2105055468 hasConcept C41895202 @default.
- W2105055468 hasConcept C52622490 @default.
- W2105055468 hasConcept C69738355 @default.
- W2105055468 hasConcept C70518039 @default.
- W2105055468 hasConcept C774472 @default.
- W2105055468 hasConcept C83665646 @default.
- W2105055468 hasConceptScore W2105055468C111030470 @default.
- W2105055468 hasConceptScore W2105055468C119857082 @default.
- W2105055468 hasConceptScore W2105055468C138885662 @default.
- W2105055468 hasConceptScore W2105055468C153180895 @default.
- W2105055468 hasConceptScore W2105055468C154945302 @default.
- W2105055468 hasConceptScore W2105055468C181367576 @default.
- W2105055468 hasConceptScore W2105055468C27438332 @default.
- W2105055468 hasConceptScore W2105055468C2776401178 @default.
- W2105055468 hasConceptScore W2105055468C31510193 @default.
- W2105055468 hasConceptScore W2105055468C33923547 @default.
- W2105055468 hasConceptScore W2105055468C41008148 @default.
- W2105055468 hasConceptScore W2105055468C41895202 @default.
- W2105055468 hasConceptScore W2105055468C52622490 @default.
- W2105055468 hasConceptScore W2105055468C69738355 @default.
- W2105055468 hasConceptScore W2105055468C70518039 @default.
- W2105055468 hasConceptScore W2105055468C774472 @default.
- W2105055468 hasConceptScore W2105055468C83665646 @default.
- W2105055468 hasIssue "1" @default.
- W2105055468 hasLocation W21050554681 @default.
- W2105055468 hasLocation W21050554682 @default.
- W2105055468 hasLocation W21050554683 @default.
- W2105055468 hasOpenAccess W2105055468 @default.
- W2105055468 hasPrimaryLocation W21050554681 @default.
- W2105055468 hasRelatedWork W1756315871 @default.
- W2105055468 hasRelatedWork W1756633271 @default.
- W2105055468 hasRelatedWork W1965275221 @default.
- W2105055468 hasRelatedWork W1986248657 @default.