FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090140268> ?p ?o ?g. }

• W3090140268 endingPage "19" @default.
• W3090140268 startingPage "1" @default.
• W3090140268 abstract "( Aim ) Multiple sclerosis is a neurological condition that may cause neurologic disability. Convolutional neural network can achieve good results, but tuning hyperparameters of CNN needs expert knowledge and are difficult and time-consuming. To identify multiple sclerosis more accurately, this article proposed a new transfer-learning-based approach. ( Method ) DenseNet-121, DenseNet-169, and DenseNet-201 neural networks were compared. In addition, we proposed the use of a composite learning factor (CLF) that assigns different learning factor to three types of layers: early frozen layers, middle layers, and late replaced layers. How to allocate layers into those three layers remains a problem. Hence, four transfer learning settings (viz., Settings A, B, C, and D) were tested and compared. A precomputation method was utilized to reduce the storage burden and accelerate the program. ( Results ) We observed that DenseNet-201-D (the layers from CP to T3 are frozen, the layers of D4 are updated with learning factor of 1, and the final new layers of FCL are randomly initialized with learning factor of 10) can achieve the best performance. The sensitivity, specificity, and accuracy of DenseNet-201-D was 98.27± 0.58, 98.35± 0.69, and 98.31± 0.53, respectively. ( Conclusion ) Our method gives better performances than state-of-the-art approaches. Furthermore, this composite learning rate gives superior results to traditional simple learning factor (SLF) strategy." @default.
• W3090140268 created "2020-10-08" @default.
• W3090140268 creator A5007987858 @default.
• W3090140268 creator A5090965728 @default.
• W3090140268 date "2020-04-30" @default.
• W3090140268 modified "2023-10-11" @default.
• W3090140268 title "DenseNet-201-Based Deep Neural Network with Composite Learning Factor and Precomputation for Multiple Sclerosis Classification" @default.
• W3090140268 cites W1148496451 @default.
• W3090140268 cites W1981166908 @default.
• W3090140268 cites W2026370547 @default.
• W3090140268 cites W2027285375 @default.
• W3090140268 cites W2050329937 @default.
• W3090140268 cites W2090797242 @default.
• W3090140268 cites W2108154570 @default.
• W3090140268 cites W2109178466 @default.
• W3090140268 cites W2194775991 @default.
• W3090140268 cites W2312523840 @default.
• W3090140268 cites W2345189929 @default.
• W3090140268 cites W2498450017 @default.
• W3090140268 cites W2584922303 @default.
• W3090140268 cites W2618241468 @default.
• W3090140268 cites W2754235618 @default.
• W3090140268 cites W2758602683 @default.
• W3090140268 cites W2762641225 @default.
• W3090140268 cites W2787890383 @default.
• W3090140268 cites W2792545481 @default.
• W3090140268 cites W2792617803 @default.
• W3090140268 cites W2801165650 @default.
• W3090140268 cites W2808597956 @default.
• W3090140268 cites W2822024738 @default.
• W3090140268 cites W2885452141 @default.
• W3090140268 cites W2900570788 @default.
• W3090140268 cites W2902753032 @default.
• W3090140268 cites W2905877654 @default.
• W3090140268 cites W2909332287 @default.
• W3090140268 cites W2910182844 @default.
• W3090140268 cites W2910342037 @default.
• W3090140268 cites W2912250162 @default.
• W3090140268 cites W2923146325 @default.
• W3090140268 doi "https://doi.org/10.1145/3341095" @default.
• W3090140268 hasPublicationYear "2020" @default.
• W3090140268 type Work @default.
• W3090140268 sameAs 3090140268 @default.
• W3090140268 citedByCount "91" @default.
• W3090140268 countsByYear W30901402682020 @default.
• W3090140268 countsByYear W30901402682021 @default.
• W3090140268 countsByYear W30901402682022 @default.
• W3090140268 countsByYear W30901402682023 @default.
• W3090140268 crossrefType "journal-article" @default.
• W3090140268 hasAuthorship W3090140268A5007987858 @default.
• W3090140268 hasAuthorship W3090140268A5090965728 @default.
• W3090140268 hasConcept C108583219 @default.
• W3090140268 hasConcept C11413529 @default.
• W3090140268 hasConcept C119857082 @default.
• W3090140268 hasConcept C150899416 @default.
• W3090140268 hasConcept C153180895 @default.
• W3090140268 hasConcept C154945302 @default.
• W3090140268 hasConcept C159379195 @default.
• W3090140268 hasConcept C199360897 @default.
• W3090140268 hasConcept C2781039887 @default.
• W3090140268 hasConcept C41008148 @default.
• W3090140268 hasConcept C45374587 @default.
• W3090140268 hasConcept C50644808 @default.
• W3090140268 hasConcept C81363708 @default.
• W3090140268 hasConcept C8642999 @default.
• W3090140268 hasConceptScore W3090140268C108583219 @default.
• W3090140268 hasConceptScore W3090140268C11413529 @default.
• W3090140268 hasConceptScore W3090140268C119857082 @default.
• W3090140268 hasConceptScore W3090140268C150899416 @default.
• W3090140268 hasConceptScore W3090140268C153180895 @default.
• W3090140268 hasConceptScore W3090140268C154945302 @default.
• W3090140268 hasConceptScore W3090140268C159379195 @default.
• W3090140268 hasConceptScore W3090140268C199360897 @default.
• W3090140268 hasConceptScore W3090140268C2781039887 @default.
• W3090140268 hasConceptScore W3090140268C41008148 @default.
• W3090140268 hasConceptScore W3090140268C45374587 @default.
• W3090140268 hasConceptScore W3090140268C50644808 @default.
• W3090140268 hasConceptScore W3090140268C81363708 @default.
• W3090140268 hasConceptScore W3090140268C8642999 @default.
• W3090140268 hasFunder F4320321001 @default.
• W3090140268 hasFunder F4320338464 @default.
• W3090140268 hasIssue "2s" @default.
• W3090140268 hasLocation W30901402681 @default.
• W3090140268 hasOpenAccess W3090140268 @default.
• W3090140268 hasPrimaryLocation W30901402681 @default.
• W3090140268 hasRelatedWork W2253429366 @default.
• W3090140268 hasRelatedWork W3003905048 @default.
• W3090140268 hasRelatedWork W3135818718 @default.
• W3090140268 hasRelatedWork W3167935049 @default.
• W3090140268 hasRelatedWork W3176438653 @default.
• W3090140268 hasRelatedWork W3183901164 @default.
• W3090140268 hasRelatedWork W4206951940 @default.
• W3090140268 hasRelatedWork W4290188444 @default.
• W3090140268 hasRelatedWork W4293868382 @default.
• W3090140268 hasRelatedWork W4382602594 @default.
• W3090140268 hasVolume "16" @default.
• W3090140268 isParatext "false" @default.
• W3090140268 isRetracted "false" @default.

• next