Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904504986> ?p ?o ?g. }
- W2904504986 abstract "Combining neuroimaging and clinical information for diagnosis, as for example behavioral tasks and genetics characteristics, is potentially beneficial but presents challenges in terms of finding the best data representation for the different sources of information. Their simple combination usually does not provide an improvement if compared with using the best source alone. In this paper, we proposed a framework based on a recent multiple kernel learning algorithm called EasyMKL and we investigated the benefits of this approach for diagnosing two different mental health diseases. The well known Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset tackling the Alzheimer Disease (AD) patients versus healthy controls classification task, and a second dataset tackling the task of classifying an heterogeneous group of depressed patients versus healthy controls. We used EasyMKL to combine a huge amount of basic kernels alongside a feature selection methodology, pursuing an optimal and sparse solution to facilitate interpretability. Our results show that the proposed approach, called EasyMKLFS, outperforms baselines (e.g. SVM and SimpleMKL), state-of-the-art random forests (RF) and feature selection (FS) methods." @default.
- W2904504986 created "2018-12-22" @default.
- W2904504986 creator A5034260726 @default.
- W2904504986 creator A5036416110 @default.
- W2904504986 creator A5040133485 @default.
- W2904504986 creator A5047980012 @default.
- W2904504986 creator A5055279410 @default.
- W2904504986 creator A5056775618 @default.
- W2904504986 creator A5071728849 @default.
- W2904504986 date "2018-12-10" @default.
- W2904504986 modified "2023-09-27" @default.
- W2904504986 title "Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important" @default.
- W2904504986 cites W102835753 @default.
- W2904504986 cites W1510073064 @default.
- W2904504986 cites W1559159361 @default.
- W2904504986 cites W1565746575 @default.
- W2904504986 cites W1696318955 @default.
- W2904504986 cites W1847168837 @default.
- W2904504986 cites W1964006502 @default.
- W2904504986 cites W1977465442 @default.
- W2904504986 cites W1978763244 @default.
- W2904504986 cites W1999693420 @default.
- W2904504986 cites W1999919402 @default.
- W2904504986 cites W2000212202 @default.
- W2904504986 cites W2001173190 @default.
- W2904504986 cites W2002677512 @default.
- W2904504986 cites W2011402106 @default.
- W2904504986 cites W2014418634 @default.
- W2904504986 cites W2023687307 @default.
- W2904504986 cites W2029866741 @default.
- W2904504986 cites W2031823405 @default.
- W2904504986 cites W2036439084 @default.
- W2904504986 cites W2058046532 @default.
- W2904504986 cites W2059223794 @default.
- W2904504986 cites W2060166505 @default.
- W2904504986 cites W2065057616 @default.
- W2904504986 cites W2065180801 @default.
- W2904504986 cites W2072794732 @default.
- W2904504986 cites W2078471201 @default.
- W2904504986 cites W2086604324 @default.
- W2904504986 cites W2091828766 @default.
- W2904504986 cites W2109743529 @default.
- W2904504986 cites W2110065044 @default.
- W2904504986 cites W2112019442 @default.
- W2904504986 cites W2116343548 @default.
- W2904504986 cites W2117063635 @default.
- W2904504986 cites W2127069950 @default.
- W2904504986 cites W2128036349 @default.
- W2904504986 cites W2128251808 @default.
- W2904504986 cites W2131823335 @default.
- W2904504986 cites W2139577967 @default.
- W2904504986 cites W2143426320 @default.
- W2904504986 cites W2146089088 @default.
- W2904504986 cites W2154340507 @default.
- W2904504986 cites W2158422390 @default.
- W2904504986 cites W2164535072 @default.
- W2904504986 cites W2170912114 @default.
- W2904504986 cites W2171188027 @default.
- W2904504986 cites W2198940986 @default.
- W2904504986 cites W2205686117 @default.
- W2904504986 cites W2221086408 @default.
- W2904504986 cites W2293865782 @default.
- W2904504986 cites W2303171129 @default.
- W2904504986 cites W2307883498 @default.
- W2904504986 cites W2354785768 @default.
- W2904504986 cites W2412958948 @default.
- W2904504986 cites W2421101021 @default.
- W2904504986 cites W2466831271 @default.
- W2904504986 cites W2527896982 @default.
- W2904504986 cites W2551056916 @default.
- W2904504986 cites W2555008851 @default.
- W2904504986 cites W2555500380 @default.
- W2904504986 cites W2563148755 @default.
- W2904504986 cites W2592343442 @default.
- W2904504986 cites W2594734910 @default.
- W2904504986 cites W2781572850 @default.
- W2904504986 cites W2884367318 @default.
- W2904504986 cites W2951792757 @default.
- W2904504986 cites W2952403599 @default.
- W2904504986 cites W3100067206 @default.
- W2904504986 cites W74362798 @default.
- W2904504986 cites W2136925113 @default.
- W2904504986 doi "https://doi.org/10.1101/484311" @default.
- W2904504986 hasPublicationYear "2018" @default.
- W2904504986 type Work @default.
- W2904504986 sameAs 2904504986 @default.
- W2904504986 citedByCount "0" @default.
- W2904504986 crossrefType "posted-content" @default.
- W2904504986 hasAuthorship W2904504986A5034260726 @default.
- W2904504986 hasAuthorship W2904504986A5036416110 @default.
- W2904504986 hasAuthorship W2904504986A5040133485 @default.
- W2904504986 hasAuthorship W2904504986A5047980012 @default.
- W2904504986 hasAuthorship W2904504986A5055279410 @default.
- W2904504986 hasAuthorship W2904504986A5056775618 @default.
- W2904504986 hasAuthorship W2904504986A5071728849 @default.
- W2904504986 hasBestOaLocation W29045049861 @default.
- W2904504986 hasConcept C114614502 @default.
- W2904504986 hasConcept C119857082 @default.
- W2904504986 hasConcept C122280245 @default.
- W2904504986 hasConcept C12267149 @default.