FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914585471> ?p ?o ?g. }

• W2914585471 endingPage "18463" @default.
• W2914585471 startingPage "18450" @default.
• W2914585471 abstract "Data imbalance issue generally exists in most medical image analysis problems and maybe getting important with the popularization of data-hungry deep learning paradigms. We explore the cutting-edge Wasserstein generative adversarial networks (WGANs) to address the data imbalance problem with oversampling on the minority classes. The WGAN can estimate the underlying distribution of a minority class to synthesize more plausible and helpful samples for the classification model. In this paper, the WGAN-based over-sampling technique is applied to augment the data to balance for the fine-grained classification of seven semantic attributes of lung nodules in computed tomography images. The fine-grained classification is carried out with a normal convolutional neural network (CNN). To further illustrate the efficacy of the WGAN-based over-sampling technique, the conventional data augmentation method commonly used in many deep learning works, the generative adversarial networks (GANs), and the deep convolutional generative adversarial networks (DCGANs) are implemented for comparison. The whole schemes of the minority oversampling and fine-grained classification are tested with the public lung imaging database consortium dataset. The experimental results suggest that the WGAN-based oversampling technique can synthesize helpful samples for the minority classes to assist the training of the CNN model and to boost the fine-grained classification performance better than the conventional data augmentation method and the two schemes of the GAN and DCGAN techniques do. It may thus suggest that the WGAN technique offers an alternative methodological option for the further deep learning on imbalanced classification studies." @default.
• W2914585471 created "2019-02-21" @default.
• W2914585471 creator A5008315702 @default.
• W2914585471 creator A5008530363 @default.
• W2914585471 creator A5012549255 @default.
• W2914585471 creator A5056431851 @default.
• W2914585471 creator A5060750009 @default.
• W2914585471 creator A5064258102 @default.
• W2914585471 creator A5077322091 @default.
• W2914585471 creator A5083811829 @default.
• W2914585471 creator A5085405438 @default.
• W2914585471 date "2019-01-01" @default.
• W2914585471 modified "2023-10-14" @default.
• W2914585471 title "WGAN-Based Synthetic Minority Over-Sampling Technique: Improving Semantic Fine-Grained Classification for Lung Nodules in CT Images" @default.
• W2914585471 cites W1630436329 @default.
• W2914585471 cites W1871050032 @default.
• W2914585471 cites W1937937026 @default.
• W2914585471 cites W1958236864 @default.
• W2914585471 cites W1974165720 @default.
• W2914585471 cites W2024223694 @default.
• W2914585471 cites W2106136950 @default.
• W2914585471 cites W2185967890 @default.
• W2914585471 cites W2322371438 @default.
• W2914585471 cites W2341106171 @default.
• W2914585471 cites W2394599079 @default.
• W2914585471 cites W2533800772 @default.
• W2914585471 cites W2543630535 @default.
• W2914585471 cites W2553191729 @default.
• W2914585471 cites W2581082771 @default.
• W2914585471 cites W2593232761 @default.
• W2914585471 cites W2598799153 @default.
• W2914585471 cites W2617128058 @default.
• W2914585471 cites W2743636956 @default.
• W2914585471 cites W2751679535 @default.
• W2914585471 cites W2777186991 @default.
• W2914585471 cites W2789713147 @default.
• W2914585471 cites W2892923422 @default.
• W2914585471 cites W2963073614 @default.
• W2914585471 cites W2963470893 @default.
• W2914585471 cites W2964024144 @default.
• W2914585471 cites W948663339 @default.
• W2914585471 cites W96995336 @default.
• W2914585471 doi "https://doi.org/10.1109/access.2019.2896409" @default.
• W2914585471 hasPublicationYear "2019" @default.
• W2914585471 type Work @default.
• W2914585471 sameAs 2914585471 @default.
• W2914585471 citedByCount "65" @default.
• W2914585471 countsByYear W29145854712019 @default.
• W2914585471 countsByYear W29145854712020 @default.
• W2914585471 countsByYear W29145854712021 @default.
• W2914585471 countsByYear W29145854712022 @default.
• W2914585471 countsByYear W29145854712023 @default.
• W2914585471 crossrefType "journal-article" @default.
• W2914585471 hasAuthorship W2914585471A5008315702 @default.
• W2914585471 hasAuthorship W2914585471A5008530363 @default.
• W2914585471 hasAuthorship W2914585471A5012549255 @default.
• W2914585471 hasAuthorship W2914585471A5056431851 @default.
• W2914585471 hasAuthorship W2914585471A5060750009 @default.
• W2914585471 hasAuthorship W2914585471A5064258102 @default.
• W2914585471 hasAuthorship W2914585471A5077322091 @default.
• W2914585471 hasAuthorship W2914585471A5083811829 @default.
• W2914585471 hasAuthorship W2914585471A5085405438 @default.
• W2914585471 hasBestOaLocation W29145854711 @default.
• W2914585471 hasConcept C106131492 @default.
• W2914585471 hasConcept C140779682 @default.
• W2914585471 hasConcept C153180895 @default.
• W2914585471 hasConcept C154945302 @default.
• W2914585471 hasConcept C31972630 @default.
• W2914585471 hasConcept C41008148 @default.
• W2914585471 hasConceptScore W2914585471C106131492 @default.
• W2914585471 hasConceptScore W2914585471C140779682 @default.
• W2914585471 hasConceptScore W2914585471C153180895 @default.
• W2914585471 hasConceptScore W2914585471C154945302 @default.
• W2914585471 hasConceptScore W2914585471C31972630 @default.
• W2914585471 hasConceptScore W2914585471C41008148 @default.
• W2914585471 hasFunder F4320321001 @default.
• W2914585471 hasFunder F4320322847 @default.
• W2914585471 hasFunder F4320334897 @default.
• W2914585471 hasFunder F4320335777 @default.
• W2914585471 hasLocation W29145854711 @default.
• W2914585471 hasOpenAccess W2914585471 @default.
• W2914585471 hasPrimaryLocation W29145854711 @default.
• W2914585471 hasRelatedWork W1891287906 @default.
• W2914585471 hasRelatedWork W1969923398 @default.
• W2914585471 hasRelatedWork W2036807459 @default.
• W2914585471 hasRelatedWork W2058170566 @default.
• W2914585471 hasRelatedWork W2166024367 @default.
• W2914585471 hasRelatedWork W2229312674 @default.
• W2914585471 hasRelatedWork W2755342338 @default.
• W2914585471 hasRelatedWork W2772917594 @default.
• W2914585471 hasRelatedWork W2775347418 @default.
• W2914585471 hasRelatedWork W3116076068 @default.
• W2914585471 hasVolume "7" @default.
• W2914585471 isParatext "false" @default.
• W2914585471 isRetracted "false" @default.
• W2914585471 magId "2914585471" @default.
• W2914585471 workType "article" @default.