Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367360246> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4367360246 endingPage "143" @default.
- W4367360246 startingPage "131" @default.
- W4367360246 abstract "By the end of 2021 in Indonesia, there was an increase in the price of basic foodstuffs, including chili. This price increase was due to farmers’ chili supply shortage because of disease that attacked chili plants in various areas. Early detection of chili plant diseases is essential to maintain the quality and productivity of crop yields. Research related to the detection of chili plant diseases has been developed by many researchers, for example, using machine learning techniques. Previous research used machine learning to classify three classes of chili diseases. The results of this research are not optimal because the amount of data used is small, so it only reaches 86% accuracy. Therefore, we propose using the Convolutional Neural Network (CNN) method, which is part of deep learning. This research contributes to building a CNN architectural model for processing small datasets. We developed the CNN architecture to process small amounts of data. The dataset consists of 5 classes: healthy, leaf curl, leaf spot, whitefly, and yellowish. The raw data obtained is pre-processed before going to the feature extraction stage. The reason for pre-processing is to homogenize the size and augment the data. The results of the pre-processing data will be used for feature extraction and classification using CNN. We also compare the results of using CNN with the DenseNet201 transfer learning model. The test results using the confusion matrix obtained an accuracy of 92% on the use of the DenseNet201 model, while on CNN, it produced an accuracy of 94%. Through these results, agricultural technology developers can use this method, especially for chili plants." @default.
- W4367360246 created "2023-04-30" @default.
- W4367360246 creator A5009683310 @default.
- W4367360246 creator A5046835421 @default.
- W4367360246 creator A5052181694 @default.
- W4367360246 creator A5065613937 @default.
- W4367360246 date "2023-01-01" @default.
- W4367360246 modified "2023-09-25" @default.
- W4367360246 title "A Model Convolutional Neural Network for Early Detection of Chili Plant Diseases in Small Datasets" @default.
- W4367360246 cites W1806891645 @default.
- W4367360246 cites W2778714099 @default.
- W4367360246 cites W2788292821 @default.
- W4367360246 cites W2943099062 @default.
- W4367360246 cites W2955193737 @default.
- W4367360246 cites W2963446712 @default.
- W4367360246 cites W3012499855 @default.
- W4367360246 cites W3021970402 @default.
- W4367360246 cites W3036905864 @default.
- W4367360246 cites W3040660552 @default.
- W4367360246 cites W3049356352 @default.
- W4367360246 cites W3093596417 @default.
- W4367360246 cites W3107312747 @default.
- W4367360246 cites W3108636283 @default.
- W4367360246 cites W3121511479 @default.
- W4367360246 cites W3140854437 @default.
- W4367360246 cites W3158773791 @default.
- W4367360246 cites W3165444657 @default.
- W4367360246 cites W3171624627 @default.
- W4367360246 cites W3202825385 @default.
- W4367360246 cites W4200376372 @default.
- W4367360246 cites W4213223813 @default.
- W4367360246 cites W4282958617 @default.
- W4367360246 cites W4284694577 @default.
- W4367360246 cites W4285235915 @default.
- W4367360246 cites W4289109135 @default.
- W4367360246 doi "https://doi.org/10.1007/978-981-99-0248-4_10" @default.
- W4367360246 hasPublicationYear "2023" @default.
- W4367360246 type Work @default.
- W4367360246 citedByCount "0" @default.
- W4367360246 crossrefType "book-chapter" @default.
- W4367360246 hasAuthorship W4367360246A5009683310 @default.
- W4367360246 hasAuthorship W4367360246A5046835421 @default.
- W4367360246 hasAuthorship W4367360246A5052181694 @default.
- W4367360246 hasAuthorship W4367360246A5065613937 @default.
- W4367360246 hasConcept C108583219 @default.
- W4367360246 hasConcept C119857082 @default.
- W4367360246 hasConcept C138602881 @default.
- W4367360246 hasConcept C150899416 @default.
- W4367360246 hasConcept C153180895 @default.
- W4367360246 hasConcept C154945302 @default.
- W4367360246 hasConcept C41008148 @default.
- W4367360246 hasConcept C52622490 @default.
- W4367360246 hasConcept C81363708 @default.
- W4367360246 hasConceptScore W4367360246C108583219 @default.
- W4367360246 hasConceptScore W4367360246C119857082 @default.
- W4367360246 hasConceptScore W4367360246C138602881 @default.
- W4367360246 hasConceptScore W4367360246C150899416 @default.
- W4367360246 hasConceptScore W4367360246C153180895 @default.
- W4367360246 hasConceptScore W4367360246C154945302 @default.
- W4367360246 hasConceptScore W4367360246C41008148 @default.
- W4367360246 hasConceptScore W4367360246C52622490 @default.
- W4367360246 hasConceptScore W4367360246C81363708 @default.
- W4367360246 hasLocation W43673602461 @default.
- W4367360246 hasOpenAccess W4367360246 @default.
- W4367360246 hasPrimaryLocation W43673602461 @default.
- W4367360246 hasRelatedWork W2732542196 @default.
- W4367360246 hasRelatedWork W2738221750 @default.
- W4367360246 hasRelatedWork W2800691917 @default.
- W4367360246 hasRelatedWork W2946016983 @default.
- W4367360246 hasRelatedWork W3018421652 @default.
- W4367360246 hasRelatedWork W3091976719 @default.
- W4367360246 hasRelatedWork W3156786002 @default.
- W4367360246 hasRelatedWork W3166467183 @default.
- W4367360246 hasRelatedWork W3192840557 @default.
- W4367360246 hasRelatedWork W4366224123 @default.
- W4367360246 isParatext "false" @default.
- W4367360246 isRetracted "false" @default.
- W4367360246 workType "book-chapter" @default.