Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281759632> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4281759632 abstract "In this work we propose efficient deep neural networks for classification that are well suited to the edge computing and cloud computing environment. These environments inherently have to deal with bandwidth limitations and bounded computational resources. Our proposed methods tend to reduce the bandwidth requirements and reduce the computational costs for running these deep learning algorithms. We extensively utilized the Discrete Cosine Transforms (DCT) to exploit the redundancy in the image datasets. In this work we present a deep neural network that predicts the most significant DCT coefficients for an image and then employs these important DCT coefficients for classification purpose. This makes the deep neural network to achieve classification by processing much less input information. Broadly two approaches were used for classification purpose. In the first approach classification was done by employing the most significant DCT coefficients and in the second approach low resolution images, constructed from a limited number of DCT coefficients were utilized for classification purpose. The experiments were performed on well-known greyscale and RGB image datasets like FASHION MNIST, CIFAR-10 and CIFAR-100. VGG-16 architecture is mainly used for classification. The experiments showed promising results and the classification accuracies achieved were almost the same as that achieved by full resolution images." @default.
- W4281759632 created "2022-06-13" @default.
- W4281759632 creator A5004726367 @default.
- W4281759632 creator A5014265935 @default.
- W4281759632 creator A5047636327 @default.
- W4281759632 date "2022-05-24" @default.
- W4281759632 modified "2023-09-27" @default.
- W4281759632 title "Utilization of DCT Coefficients for the Classification of Standard Datasets in Cloud/Edge Computing Environment" @default.
- W4281759632 cites W114517082 @default.
- W4281759632 cites W1977993134 @default.
- W4281759632 cites W2031614119 @default.
- W4281759632 cites W2058760036 @default.
- W4281759632 cites W2168162153 @default.
- W4281759632 cites W2416799949 @default.
- W4281759632 cites W2767072113 @default.
- W4281759632 cites W2768975974 @default.
- W4281759632 cites W2775394714 @default.
- W4281759632 cites W2790813572 @default.
- W4281759632 cites W2804733524 @default.
- W4281759632 cites W2903374561 @default.
- W4281759632 cites W2952596784 @default.
- W4281759632 cites W2958414331 @default.
- W4281759632 cites W2963699903 @default.
- W4281759632 cites W2981374454 @default.
- W4281759632 cites W3000214932 @default.
- W4281759632 cites W3011628663 @default.
- W4281759632 cites W3016425051 @default.
- W4281759632 cites W3016620475 @default.
- W4281759632 cites W3021951958 @default.
- W4281759632 cites W3035925910 @default.
- W4281759632 cites W3096238699 @default.
- W4281759632 cites W3099895171 @default.
- W4281759632 doi "https://doi.org/10.1109/icodt255437.2022.9787466" @default.
- W4281759632 hasPublicationYear "2022" @default.
- W4281759632 type Work @default.
- W4281759632 citedByCount "1" @default.
- W4281759632 countsByYear W42817596322023 @default.
- W4281759632 crossrefType "proceedings-article" @default.
- W4281759632 hasAuthorship W4281759632A5004726367 @default.
- W4281759632 hasAuthorship W4281759632A5014265935 @default.
- W4281759632 hasAuthorship W4281759632A5047636327 @default.
- W4281759632 hasConcept C108583219 @default.
- W4281759632 hasConcept C111919701 @default.
- W4281759632 hasConcept C115961682 @default.
- W4281759632 hasConcept C152124472 @default.
- W4281759632 hasConcept C153180895 @default.
- W4281759632 hasConcept C154945302 @default.
- W4281759632 hasConcept C190502265 @default.
- W4281759632 hasConcept C2221639 @default.
- W4281759632 hasConcept C41008148 @default.
- W4281759632 hasConcept C50644808 @default.
- W4281759632 hasConcept C75294576 @default.
- W4281759632 hasConcept C79974875 @default.
- W4281759632 hasConceptScore W4281759632C108583219 @default.
- W4281759632 hasConceptScore W4281759632C111919701 @default.
- W4281759632 hasConceptScore W4281759632C115961682 @default.
- W4281759632 hasConceptScore W4281759632C152124472 @default.
- W4281759632 hasConceptScore W4281759632C153180895 @default.
- W4281759632 hasConceptScore W4281759632C154945302 @default.
- W4281759632 hasConceptScore W4281759632C190502265 @default.
- W4281759632 hasConceptScore W4281759632C2221639 @default.
- W4281759632 hasConceptScore W4281759632C41008148 @default.
- W4281759632 hasConceptScore W4281759632C50644808 @default.
- W4281759632 hasConceptScore W4281759632C75294576 @default.
- W4281759632 hasConceptScore W4281759632C79974875 @default.
- W4281759632 hasLocation W42817596321 @default.
- W4281759632 hasOpenAccess W4281759632 @default.
- W4281759632 hasPrimaryLocation W42817596321 @default.
- W4281759632 hasRelatedWork W2167735388 @default.
- W4281759632 hasRelatedWork W2774265021 @default.
- W4281759632 hasRelatedWork W2810865670 @default.
- W4281759632 hasRelatedWork W2888503998 @default.
- W4281759632 hasRelatedWork W3120206105 @default.
- W4281759632 hasRelatedWork W3156786002 @default.
- W4281759632 hasRelatedWork W4220663171 @default.
- W4281759632 hasRelatedWork W4309224979 @default.
- W4281759632 hasRelatedWork W4317374280 @default.
- W4281759632 hasRelatedWork W564581980 @default.
- W4281759632 isParatext "false" @default.
- W4281759632 isRetracted "false" @default.
- W4281759632 workType "article" @default.