Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313332867> ?p ?o ?g. }
- W4313332867 endingPage "102459" @default.
- W4313332867 startingPage "102459" @default.
- W4313332867 abstract "Chicken coccidiosis is a disease caused by Eimeria spp. and costs the broiler industry more than 14 billion dollars per year globally. Different chicken Eimeria species vary significantly in pathogenicity and virulence, so the classification of different chicken Eimeria species is of great significance for the epidemiological survey and related prevention and control. The microscopic morphological examination for their classification was widely used in clinical applications, but it is a time-consuming task and needs expertise. To increase the classification efficiency and accuracy, a novel model integrating transformer and convolutional neural network (CNN), named Residual-Transformer-Fine-Grained (ResTFG), was proposed and evaluated for fine-grained classification of microscopic images of seven chicken Eimeria species. The results showed that ResTFG achieved the best performance with high accuracy and low cost compared with traditional models. Specifically, the parameters, inference speed and overall accuracy of ResTFG are 1.95M, 256 FPS and 96.9%, respectively, which are 10.9 times lighter, 1.5 times faster and 2.7% higher in accuracy than the benchmark model. In addition, ResTFG showed better performance on the classification of the more virulent species. The results of ablation experiments showed that CNN or Transformer alone had model accuracies of only 89.8% and 87.0%, which proved that the improved performance of ResTFG was benefit from the complementary effect of CNN's local feature extraction and transformer's global receptive field. This study invented a reliable, low-cost, and promising deep learning model for the automatic fine-grain classification of chicken Eimeria species, which could potentially be embedded in microscopic devices to improve the work efficiency of researchers and extended to other parasite ova, and applied to other agricultural tasks as a backbone." @default.
- W4313332867 created "2023-01-06" @default.
- W4313332867 creator A5000313503 @default.
- W4313332867 creator A5001616465 @default.
- W4313332867 creator A5015816121 @default.
- W4313332867 creator A5024739317 @default.
- W4313332867 creator A5031863631 @default.
- W4313332867 creator A5032652048 @default.
- W4313332867 creator A5073019631 @default.
- W4313332867 date "2023-03-01" @default.
- W4313332867 modified "2023-09-27" @default.
- W4313332867 title "A reliable and low-cost deep learning model integrating convolutional neural network and transformer structure for fine-grained classification of chicken Eimeria species" @default.
- W4313332867 cites W1904584449 @default.
- W4313332867 cites W1966080581 @default.
- W4313332867 cites W2007404171 @default.
- W4313332867 cites W2071663063 @default.
- W4313332867 cites W2581082771 @default.
- W4313332867 cites W2606222025 @default.
- W4313332867 cites W2618752674 @default.
- W4313332867 cites W2899308925 @default.
- W4313332867 cites W2959784504 @default.
- W4313332867 cites W2975565280 @default.
- W4313332867 cites W2989702950 @default.
- W4313332867 cites W3007403657 @default.
- W4313332867 cites W3084637486 @default.
- W4313332867 cites W3158845203 @default.
- W4313332867 cites W3158902352 @default.
- W4313332867 cites W3160230758 @default.
- W4313332867 cites W3170971507 @default.
- W4313332867 cites W3188404242 @default.
- W4313332867 cites W3207030688 @default.
- W4313332867 cites W4200269626 @default.
- W4313332867 cites W4200349706 @default.
- W4313332867 doi "https://doi.org/10.1016/j.psj.2022.102459" @default.
- W4313332867 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36682127" @default.
- W4313332867 hasPublicationYear "2023" @default.
- W4313332867 type Work @default.
- W4313332867 citedByCount "1" @default.
- W4313332867 countsByYear W43133328672023 @default.
- W4313332867 crossrefType "journal-article" @default.
- W4313332867 hasAuthorship W4313332867A5000313503 @default.
- W4313332867 hasAuthorship W4313332867A5001616465 @default.
- W4313332867 hasAuthorship W4313332867A5015816121 @default.
- W4313332867 hasAuthorship W4313332867A5024739317 @default.
- W4313332867 hasAuthorship W4313332867A5031863631 @default.
- W4313332867 hasAuthorship W4313332867A5032652048 @default.
- W4313332867 hasAuthorship W4313332867A5073019631 @default.
- W4313332867 hasBestOaLocation W43133328671 @default.
- W4313332867 hasConcept C108583219 @default.
- W4313332867 hasConcept C11413529 @default.
- W4313332867 hasConcept C119599485 @default.
- W4313332867 hasConcept C127413603 @default.
- W4313332867 hasConcept C153180895 @default.
- W4313332867 hasConcept C154945302 @default.
- W4313332867 hasConcept C155512373 @default.
- W4313332867 hasConcept C165801399 @default.
- W4313332867 hasConcept C2776214188 @default.
- W4313332867 hasConcept C2777976947 @default.
- W4313332867 hasConcept C41008148 @default.
- W4313332867 hasConcept C42972112 @default.
- W4313332867 hasConcept C50644808 @default.
- W4313332867 hasConcept C66322947 @default.
- W4313332867 hasConcept C71924100 @default.
- W4313332867 hasConcept C81363708 @default.
- W4313332867 hasConcept C86803240 @default.
- W4313332867 hasConceptScore W4313332867C108583219 @default.
- W4313332867 hasConceptScore W4313332867C11413529 @default.
- W4313332867 hasConceptScore W4313332867C119599485 @default.
- W4313332867 hasConceptScore W4313332867C127413603 @default.
- W4313332867 hasConceptScore W4313332867C153180895 @default.
- W4313332867 hasConceptScore W4313332867C154945302 @default.
- W4313332867 hasConceptScore W4313332867C155512373 @default.
- W4313332867 hasConceptScore W4313332867C165801399 @default.
- W4313332867 hasConceptScore W4313332867C2776214188 @default.
- W4313332867 hasConceptScore W4313332867C2777976947 @default.
- W4313332867 hasConceptScore W4313332867C41008148 @default.
- W4313332867 hasConceptScore W4313332867C42972112 @default.
- W4313332867 hasConceptScore W4313332867C50644808 @default.
- W4313332867 hasConceptScore W4313332867C66322947 @default.
- W4313332867 hasConceptScore W4313332867C71924100 @default.
- W4313332867 hasConceptScore W4313332867C81363708 @default.
- W4313332867 hasConceptScore W4313332867C86803240 @default.
- W4313332867 hasIssue "3" @default.
- W4313332867 hasLocation W43133328671 @default.
- W4313332867 hasLocation W43133328672 @default.
- W4313332867 hasLocation W43133328673 @default.
- W4313332867 hasOpenAccess W4313332867 @default.
- W4313332867 hasPrimaryLocation W43133328671 @default.
- W4313332867 hasRelatedWork W2731899572 @default.
- W4313332867 hasRelatedWork W2782645198 @default.
- W4313332867 hasRelatedWork W2999805992 @default.
- W4313332867 hasRelatedWork W3011074480 @default.
- W4313332867 hasRelatedWork W3116150086 @default.
- W4313332867 hasRelatedWork W3133861977 @default.
- W4313332867 hasRelatedWork W4200173597 @default.
- W4313332867 hasRelatedWork W4291897433 @default.
- W4313332867 hasRelatedWork W4312417841 @default.
- W4313332867 hasRelatedWork W4321369474 @default.