Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317505885> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4317505885 endingPage "508" @default.
- W4317505885 startingPage "508" @default.
- W4317505885 abstract "It is of great practical significance to quickly, accurately, and effectively identify the effects of rice diseases on rice yield. This paper proposes a rice disease identification method based on an improved DenseNet network (DenseNet). This method uses DenseNet as the benchmark model and uses the channel attention mechanism squeeze-and-excitation to strengthen the favorable features, while suppressing the unfavorable features. Then, depth wise separable convolutions are introduced to replace some standard convolutions in the dense network to improve the parameter utilization and training speed. Using the AdaBound algorithm, combined with the adaptive optimization method, the parameter adjustment time reduces. In the experiments on five kinds of rice disease datasets, the average classification accuracy of the method in this paper is 99.4%, which is 13.8 percentage points higher than the original model. At the same time, it is compared with other existing recognition methods, such as ResNet, VGG, and Vision Transformer. The recognition accuracy of this method is higher, realizes the effective classification of rice disease images, and provides a new method for the development of crop disease identification technology and smart agriculture." @default.
- W4317505885 created "2023-01-20" @default.
- W4317505885 creator A5013863926 @default.
- W4317505885 creator A5029762183 @default.
- W4317505885 creator A5061758605 @default.
- W4317505885 creator A5071898642 @default.
- W4317505885 creator A5072153666 @default.
- W4317505885 creator A5087677226 @default.
- W4317505885 date "2023-01-18" @default.
- W4317505885 modified "2023-10-09" @default.
- W4317505885 title "Rice Disease Identification Method Based on Attention Mechanism and Deep Dense Network" @default.
- W4317505885 cites W1932469787 @default.
- W4317505885 cites W2194775991 @default.
- W4317505885 cites W2412782625 @default.
- W4317505885 cites W2550409828 @default.
- W4317505885 cites W2750506686 @default.
- W4317505885 cites W2784025535 @default.
- W4317505885 cites W2785932184 @default.
- W4317505885 cites W2886590014 @default.
- W4317505885 cites W2891667148 @default.
- W4317505885 cites W2902625477 @default.
- W4317505885 cites W2919115771 @default.
- W4317505885 cites W2936718694 @default.
- W4317505885 cites W2943723147 @default.
- W4317505885 cites W2963420686 @default.
- W4317505885 cites W2963446712 @default.
- W4317505885 cites W2963881378 @default.
- W4317505885 cites W2981207549 @default.
- W4317505885 cites W2999247481 @default.
- W4317505885 cites W3006483102 @default.
- W4317505885 cites W3034173830 @default.
- W4317505885 cites W3046199400 @default.
- W4317505885 cites W3119027282 @default.
- W4317505885 cites W3124944382 @default.
- W4317505885 cites W3132328762 @default.
- W4317505885 cites W3136213652 @default.
- W4317505885 cites W3163327790 @default.
- W4317505885 cites W3167121034 @default.
- W4317505885 cites W4224274704 @default.
- W4317505885 cites W4306760222 @default.
- W4317505885 doi "https://doi.org/10.3390/electronics12030508" @default.
- W4317505885 hasPublicationYear "2023" @default.
- W4317505885 type Work @default.
- W4317505885 citedByCount "2" @default.
- W4317505885 countsByYear W43175058852023 @default.
- W4317505885 crossrefType "journal-article" @default.
- W4317505885 hasAuthorship W4317505885A5013863926 @default.
- W4317505885 hasAuthorship W4317505885A5029762183 @default.
- W4317505885 hasAuthorship W4317505885A5061758605 @default.
- W4317505885 hasAuthorship W4317505885A5071898642 @default.
- W4317505885 hasAuthorship W4317505885A5072153666 @default.
- W4317505885 hasAuthorship W4317505885A5087677226 @default.
- W4317505885 hasBestOaLocation W43175058851 @default.
- W4317505885 hasConcept C116834253 @default.
- W4317505885 hasConcept C119857082 @default.
- W4317505885 hasConcept C124101348 @default.
- W4317505885 hasConcept C153180895 @default.
- W4317505885 hasConcept C154945302 @default.
- W4317505885 hasConcept C41008148 @default.
- W4317505885 hasConcept C59822182 @default.
- W4317505885 hasConcept C86803240 @default.
- W4317505885 hasConceptScore W4317505885C116834253 @default.
- W4317505885 hasConceptScore W4317505885C119857082 @default.
- W4317505885 hasConceptScore W4317505885C124101348 @default.
- W4317505885 hasConceptScore W4317505885C153180895 @default.
- W4317505885 hasConceptScore W4317505885C154945302 @default.
- W4317505885 hasConceptScore W4317505885C41008148 @default.
- W4317505885 hasConceptScore W4317505885C59822182 @default.
- W4317505885 hasConceptScore W4317505885C86803240 @default.
- W4317505885 hasFunder F4320321001 @default.
- W4317505885 hasIssue "3" @default.
- W4317505885 hasLocation W43175058851 @default.
- W4317505885 hasLocation W43175058852 @default.
- W4317505885 hasOpenAccess W4317505885 @default.
- W4317505885 hasPrimaryLocation W43175058851 @default.
- W4317505885 hasRelatedWork W2961085424 @default.
- W4317505885 hasRelatedWork W3046775127 @default.
- W4317505885 hasRelatedWork W3170094116 @default.
- W4317505885 hasRelatedWork W4205958290 @default.
- W4317505885 hasRelatedWork W4285260836 @default.
- W4317505885 hasRelatedWork W4286629047 @default.
- W4317505885 hasRelatedWork W4306321456 @default.
- W4317505885 hasRelatedWork W4306674287 @default.
- W4317505885 hasRelatedWork W4386462264 @default.
- W4317505885 hasRelatedWork W4224009465 @default.
- W4317505885 hasVolume "12" @default.
- W4317505885 isParatext "false" @default.
- W4317505885 isRetracted "false" @default.
- W4317505885 workType "article" @default.