Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285235915> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4285235915 endingPage "95" @default.
- W4285235915 startingPage "85" @default.
- W4285235915 abstract "Image classification can be used in a variety of fields, including chicken farming, where it can be used to monitor incubator conditions by capturing the image in the machine and then using transfer learning to classify the image in the incubator. This study has a problem with obtaining the highest accuracy while also reducing overfitting in the model, to obtain classification results with the expected accuracy, this study employs three algorithms: VGG16, InceptionV3, and Deep Learning. Each algorithm will be tested on a dataset comprised of three classes: egg, chick, and hatched egg. There are 1470 images in the chick class, 1719 images in the egg class, and 1715 images in the hatched egg class. In the training and validation processes, researchers also do some data preprocessing, such as augmentation for data adjustment. The accuracy of each algorithm was determined in this study; VGG16 had an accuracy of 0.90, while InceptionV3 had an accuracy of 0.97. Deep Learning has chosen the model with the highest accuracy out of the two that were created. The accuracy of this Deep Learning model is 0.8125. This research is dealing with the issue of overfitting as it develops the Deep Learning architecture. However, it can be reduced by adding several Dropout layers to the Deep Learning architecture. Observations made during the research that each algorithm has a different level of accuracy because the architecture of each algorithm is different, even though researchers use the same dataset and testing environment. Transfer Learning using VGG16 and InceptionV3 has an accuracy of more than 90% in this study. Based on the study's findings, it is possible to conclude that using transfer learning and adding a dropout layer can produce high accuracy while reducing overfitting." @default.
- W4285235915 created "2022-07-14" @default.
- W4285235915 creator A5047541691 @default.
- W4285235915 creator A5053381807 @default.
- W4285235915 creator A5062432432 @default.
- W4285235915 creator A5065613937 @default.
- W4285235915 date "2022-01-01" @default.
- W4285235915 modified "2023-09-29" @default.
- W4285235915 title "Image Classification for Egg Incubator Using Transfer Learning VGG16 and InceptionV3" @default.
- W4285235915 cites W2044097773 @default.
- W4285235915 cites W2062227835 @default.
- W4285235915 cites W2165698076 @default.
- W4285235915 cites W2767898453 @default.
- W4285235915 cites W2769497098 @default.
- W4285235915 cites W2770687010 @default.
- W4285235915 cites W2798686767 @default.
- W4285235915 cites W2807693264 @default.
- W4285235915 cites W2893483035 @default.
- W4285235915 cites W2897153899 @default.
- W4285235915 cites W2922073769 @default.
- W4285235915 cites W2954436734 @default.
- W4285235915 cites W2974077930 @default.
- W4285235915 cites W2987286712 @default.
- W4285235915 cites W3011664876 @default.
- W4285235915 cites W3012321054 @default.
- W4285235915 cites W3031794424 @default.
- W4285235915 cites W3038484461 @default.
- W4285235915 cites W3134935272 @default.
- W4285235915 cites W3160603086 @default.
- W4285235915 cites W3163277709 @default.
- W4285235915 doi "https://doi.org/10.1007/978-981-19-1804-9_7" @default.
- W4285235915 hasPublicationYear "2022" @default.
- W4285235915 type Work @default.
- W4285235915 citedByCount "2" @default.
- W4285235915 countsByYear W42852359152023 @default.
- W4285235915 crossrefType "book-chapter" @default.
- W4285235915 hasAuthorship W4285235915A5047541691 @default.
- W4285235915 hasAuthorship W4285235915A5053381807 @default.
- W4285235915 hasAuthorship W4285235915A5062432432 @default.
- W4285235915 hasAuthorship W4285235915A5065613937 @default.
- W4285235915 hasConcept C108583219 @default.
- W4285235915 hasConcept C119857082 @default.
- W4285235915 hasConcept C150899416 @default.
- W4285235915 hasConcept C153180895 @default.
- W4285235915 hasConcept C154945302 @default.
- W4285235915 hasConcept C22019652 @default.
- W4285235915 hasConcept C2776145597 @default.
- W4285235915 hasConcept C2777212361 @default.
- W4285235915 hasConcept C34736171 @default.
- W4285235915 hasConcept C41008148 @default.
- W4285235915 hasConcept C50644808 @default.
- W4285235915 hasConceptScore W4285235915C108583219 @default.
- W4285235915 hasConceptScore W4285235915C119857082 @default.
- W4285235915 hasConceptScore W4285235915C150899416 @default.
- W4285235915 hasConceptScore W4285235915C153180895 @default.
- W4285235915 hasConceptScore W4285235915C154945302 @default.
- W4285235915 hasConceptScore W4285235915C22019652 @default.
- W4285235915 hasConceptScore W4285235915C2776145597 @default.
- W4285235915 hasConceptScore W4285235915C2777212361 @default.
- W4285235915 hasConceptScore W4285235915C34736171 @default.
- W4285235915 hasConceptScore W4285235915C41008148 @default.
- W4285235915 hasConceptScore W4285235915C50644808 @default.
- W4285235915 hasLocation W42852359151 @default.
- W4285235915 hasOpenAccess W4285235915 @default.
- W4285235915 hasPrimaryLocation W42852359151 @default.
- W4285235915 hasRelatedWork W2997709384 @default.
- W4285235915 hasRelatedWork W3012393889 @default.
- W4285235915 hasRelatedWork W3099765033 @default.
- W4285235915 hasRelatedWork W3186919929 @default.
- W4285235915 hasRelatedWork W3195938642 @default.
- W4285235915 hasRelatedWork W4200442073 @default.
- W4285235915 hasRelatedWork W4213299466 @default.
- W4285235915 hasRelatedWork W4220996320 @default.
- W4285235915 hasRelatedWork W4312200629 @default.
- W4285235915 hasRelatedWork W4313289428 @default.
- W4285235915 isParatext "false" @default.
- W4285235915 isRetracted "false" @default.
- W4285235915 workType "book-chapter" @default.