Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176294016> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3176294016 abstract "The conventional spatial convolution layers in the Convolutional Neural Networks (CNNs) are computationally expensive at the point where the training time could take days unless the number of layers, the number of training images or the size of the training images are reduced. The image size of 256x256 pixels is commonly used for most of the applications of CNN, but this image size is too small for applications like Diabetic Retinopathy (DR) classification where the image details are important for accurate classification. This research proposed Frequency Domain Convolution (FDC) and Frequency Domain Pooling (FDP) layers which were built with RFFT, kernel initialization strategy, convolution artifact removal and Channel Independent Convolution (CIC) to replace the conventional convolution and pooling layers. The FDC and FDP layers are used to build a Frequency Domain Convolutional Neural Network (FDCNN) to accelerate the training of large images for DR classification. The Full FDC layer is an extension of the FDC layer to allow direct use in conventional CNNs, it is also used to modify the VGG16 architecture. FDCNN is shown to be at least 54.21% faster and 70.74% more memory efficient compared to an equivalent CNN architecture. The modified VGG16 architecture with Full FDC layer is reported to achieve a shorter training time and a higher accuracy at 95.63% compared to the original VGG16 architecture for DR classification." @default.
- W3176294016 created "2021-07-05" @default.
- W3176294016 creator A5049821918 @default.
- W3176294016 creator A5056603982 @default.
- W3176294016 creator A5074754590 @default.
- W3176294016 date "2021-06-24" @default.
- W3176294016 modified "2023-09-27" @default.
- W3176294016 title "Frequency Domain Convolutional Neural Network: Accelerated CNN for Large Diabetic Retinopathy Image Classification." @default.
- W3176294016 cites W107968503 @default.
- W3176294016 cites W123426918 @default.
- W3176294016 cites W1677182931 @default.
- W3176294016 cites W1839118408 @default.
- W3176294016 cites W1922123711 @default.
- W3176294016 cites W2049822456 @default.
- W3176294016 cites W2511422297 @default.
- W3176294016 cites W2567482749 @default.
- W3176294016 cites W2769713325 @default.
- W3176294016 cites W2809489644 @default.
- W3176294016 cites W2963512705 @default.
- W3176294016 cites W2973658194 @default.
- W3176294016 cites W2981826026 @default.
- W3176294016 cites W3035941285 @default.
- W3176294016 cites W3036263410 @default.
- W3176294016 hasPublicationYear "2021" @default.
- W3176294016 type Work @default.
- W3176294016 sameAs 3176294016 @default.
- W3176294016 citedByCount "0" @default.
- W3176294016 crossrefType "posted-content" @default.
- W3176294016 hasAuthorship W3176294016A5049821918 @default.
- W3176294016 hasAuthorship W3176294016A5056603982 @default.
- W3176294016 hasAuthorship W3176294016A5074754590 @default.
- W3176294016 hasConcept C114466953 @default.
- W3176294016 hasConcept C114614502 @default.
- W3176294016 hasConcept C115961682 @default.
- W3176294016 hasConcept C153180895 @default.
- W3176294016 hasConcept C154945302 @default.
- W3176294016 hasConcept C199360897 @default.
- W3176294016 hasConcept C31972630 @default.
- W3176294016 hasConcept C33923547 @default.
- W3176294016 hasConcept C41008148 @default.
- W3176294016 hasConcept C45347329 @default.
- W3176294016 hasConcept C50644808 @default.
- W3176294016 hasConcept C70437156 @default.
- W3176294016 hasConcept C74193536 @default.
- W3176294016 hasConcept C75294576 @default.
- W3176294016 hasConcept C81363708 @default.
- W3176294016 hasConceptScore W3176294016C114466953 @default.
- W3176294016 hasConceptScore W3176294016C114614502 @default.
- W3176294016 hasConceptScore W3176294016C115961682 @default.
- W3176294016 hasConceptScore W3176294016C153180895 @default.
- W3176294016 hasConceptScore W3176294016C154945302 @default.
- W3176294016 hasConceptScore W3176294016C199360897 @default.
- W3176294016 hasConceptScore W3176294016C31972630 @default.
- W3176294016 hasConceptScore W3176294016C33923547 @default.
- W3176294016 hasConceptScore W3176294016C41008148 @default.
- W3176294016 hasConceptScore W3176294016C45347329 @default.
- W3176294016 hasConceptScore W3176294016C50644808 @default.
- W3176294016 hasConceptScore W3176294016C70437156 @default.
- W3176294016 hasConceptScore W3176294016C74193536 @default.
- W3176294016 hasConceptScore W3176294016C75294576 @default.
- W3176294016 hasConceptScore W3176294016C81363708 @default.
- W3176294016 hasLocation W31762940161 @default.
- W3176294016 hasOpenAccess W3176294016 @default.
- W3176294016 hasPrimaryLocation W31762940161 @default.
- W3176294016 hasRelatedWork W2772629455 @default.
- W3176294016 hasRelatedWork W2777685882 @default.
- W3176294016 hasRelatedWork W2786532341 @default.
- W3176294016 hasRelatedWork W2790669298 @default.
- W3176294016 hasRelatedWork W2790739947 @default.
- W3176294016 hasRelatedWork W2912251751 @default.
- W3176294016 hasRelatedWork W2964105559 @default.
- W3176294016 hasRelatedWork W2964140963 @default.
- W3176294016 hasRelatedWork W2964470339 @default.
- W3176294016 hasRelatedWork W2972786891 @default.
- W3176294016 hasRelatedWork W2989808579 @default.
- W3176294016 hasRelatedWork W3150757912 @default.
- W3176294016 hasRelatedWork W3197240722 @default.
- W3176294016 hasRelatedWork W3200759179 @default.
- W3176294016 hasRelatedWork W3200876444 @default.
- W3176294016 hasRelatedWork W2961288286 @default.
- W3176294016 hasRelatedWork W2961303757 @default.
- W3176294016 hasRelatedWork W3013134080 @default.
- W3176294016 hasRelatedWork W3019913511 @default.
- W3176294016 hasRelatedWork W3125966467 @default.
- W3176294016 isParatext "false" @default.
- W3176294016 isRetracted "false" @default.
- W3176294016 magId "3176294016" @default.
- W3176294016 workType "article" @default.