FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W281036081> ?p ?o ?g. }

• W281036081 endingPage "2587" @default.
• W281036081 startingPage "2569" @default.
• W281036081 abstract "Recently, neuroimaging-based Alzheimer's disease (AD) or mild cognitive impairment (MCI) diagnosis has attracted researchers in the field, due to the increasing prevalence of the diseases. Unfortunately, the unfavorable high-dimensional nature of neuroimaging data, but a limited small number of samples available, makes it challenging to build a robust computer-aided diagnosis system. Machine learning techniques have been considered as a useful tool in this respect and, among various methods, sparse regression has shown its validity in the literature. However, to our best knowledge, the existing sparse regression methods mostly try to select features based on the optimal regression coefficients in one step. We argue that since the training feature vectors are composed of both informative and uninformative or less informative features, the resulting optimal regression coefficients are inevidently affected by the uninformative or less informative features. To this end, we first propose a novel deep architecture to recursively discard uninformative features by performing sparse multi-task learning in a hierarchical fashion. We further hypothesize that the optimal regression coefficients reflect the relative importance of features in representing the target response variables. In this regard, we use the optimal regression coefficients learned in one hierarchy as feature weighting factors in the following hierarchy, and formulate a weighted sparse multi-task learning method. Lastly, we also take into account the distributional characteristics of samples per class and use clustering-induced subclass label vectors as target response values in our sparse regression model. In our experiments on the ADNI cohort, we performed both binary and multi-class classification tasks in AD/MCI diagnosis and showed the superiority of the proposed method by comparing with the state-of-the-art methods." @default.
• W281036081 created "2016-06-24" @default.
• W281036081 creator A5000937401 @default.
• W281036081 creator A5011014617 @default.
• W281036081 creator A5033720496 @default.
• W281036081 date "2015-05-21" @default.
• W281036081 modified "2023-10-14" @default.
• W281036081 title "Deep sparse multi-task learning for feature selection in Alzheimer’s disease diagnosis" @default.
• W281036081 cites W126307077 @default.
• W281036081 cites W1522806115 @default.
• W281036081 cites W1566672487 @default.
• W281036081 cites W187870010 @default.
• W281036081 cites W1964421503 @default.
• W281036081 cites W1966890608 @default.
• W281036081 cites W1970684162 @default.
• W281036081 cites W1970704418 @default.
• W281036081 cites W1970957555 @default.
• W281036081 cites W1972619838 @default.
• W281036081 cites W1974874858 @default.
• W281036081 cites W1979587499 @default.
• W281036081 cites W1980076857 @default.
• W281036081 cites W1987157607 @default.
• W281036081 cites W1991451437 @default.
• W281036081 cites W1992054897 @default.
• W281036081 cites W1998710995 @default.
• W281036081 cites W1999893542 @default.
• W281036081 cites W2000292092 @default.
• W281036081 cites W2017855408 @default.
• W281036081 cites W2024713473 @default.
• W281036081 cites W2025262281 @default.
• W281036081 cites W2028633780 @default.
• W281036081 cites W2031967811 @default.
• W281036081 cites W2032365301 @default.
• W281036081 cites W2041142744 @default.
• W281036081 cites W2041792754 @default.
• W281036081 cites W2052742260 @default.
• W281036081 cites W2054540100 @default.
• W281036081 cites W2059484129 @default.
• W281036081 cites W2065180801 @default.
• W281036081 cites W2075588526 @default.
• W281036081 cites W2078551663 @default.
• W281036081 cites W2078563723 @default.
• W281036081 cites W2078648621 @default.
• W281036081 cites W2084177652 @default.
• W281036081 cites W2085558649 @default.
• W281036081 cites W2090537659 @default.
• W281036081 cites W2095377654 @default.
• W281036081 cites W2096029372 @default.
• W281036081 cites W2097966127 @default.
• W281036081 cites W2102508963 @default.
• W281036081 cites W2104986440 @default.
• W281036081 cites W2115865170 @default.
• W281036081 cites W2128058309 @default.
• W281036081 cites W2128251808 @default.
• W281036081 cites W2129030910 @default.
• W281036081 cites W2130623086 @default.
• W281036081 cites W2133703021 @default.
• W281036081 cites W2134039594 @default.
• W281036081 cites W2136573752 @default.
• W281036081 cites W2138019504 @default.
• W281036081 cites W2138960684 @default.
• W281036081 cites W2139212933 @default.
• W281036081 cites W2139784227 @default.
• W281036081 cites W2145473366 @default.
• W281036081 cites W2146089088 @default.
• W281036081 cites W2157751286 @default.
• W281036081 cites W2157848968 @default.
• W281036081 cites W2158063156 @default.
• W281036081 cites W2158289918 @default.
• W281036081 cites W2164768417 @default.
• W281036081 cites W2165232124 @default.
• W281036081 cites W2167638846 @default.
• W281036081 cites W2889574304 @default.
• W281036081 cites W2969438869 @default.
• W281036081 doi "https://doi.org/10.1007/s00429-015-1059-y" @default.
• W281036081 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/4714963" @default.
• W281036081 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25993900" @default.
• W281036081 hasPublicationYear "2015" @default.
• W281036081 type Work @default.
• W281036081 sameAs 281036081 @default.
• W281036081 citedByCount "115" @default.
• W281036081 countsByYear W2810360812015 @default.
• W281036081 countsByYear W2810360812016 @default.
• W281036081 countsByYear W2810360812017 @default.
• W281036081 countsByYear W2810360812018 @default.
• W281036081 countsByYear W2810360812019 @default.
• W281036081 countsByYear W2810360812020 @default.
• W281036081 countsByYear W2810360812021 @default.
• W281036081 countsByYear W2810360812022 @default.
• W281036081 countsByYear W2810360812023 @default.
• W281036081 crossrefType "journal-article" @default.
• W281036081 hasAuthorship W281036081A5000937401 @default.
• W281036081 hasAuthorship W281036081A5011014617 @default.
• W281036081 hasAuthorship W281036081A5033720496 @default.
• W281036081 hasBestOaLocation W2810360812 @default.
• W281036081 hasConcept C105795698 @default.
• W281036081 hasConcept C118552586 @default.
• W281036081 hasConcept C119857082 @default.

• next