Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206899080> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3206899080 endingPage "140580" @default.
- W3206899080 startingPage "140565" @default.
- W3206899080 abstract "Convolutional neural networks have demonstrated state-of-the-art performance in image classification and various other computer vision tasks. Plant disease detection is an important area of deep learning which has been addressed by many recent methods. However, there is a dire need to optimize these solutions for resource-constrained portable devices such as smartphones. This is a challenging problem because deep learning models are resource extensive in nature. This paper proposes an efficient method to systematically classify plant disease symptoms using convolutional neural networks. These networks are memory efficient and when coupled with the proposed training configuration it enables rapid development of industrial applications by reducing the training times. Another critical problem arises with the improper distribution of samples among classes known as the class imbalance problem, which is addressed by employing a simple statistical methodology. Transfer learning is a known technique for training small datasets which transfers pre-trained weights learned on a large dataset. However, during transfer learning, negative transfer learning is a common problem. Therefore, a stepwise transfer learning approach is proposed which can help in fast convergence, while reducing overfitting and preventing negative transfer learning during knowledge transfer across domains. The system is trained and evaluated on two plant disease datasets i.e., PlantVillage (a publicly available dataset) and pepper disease dataset provided by the National Institute of Horticultural and Herbal Science, Republic of Korea. The pepper dataset is particularly challenging as it contains images from different parts of the plant such as the leaf, pulp, and stem. The proposed system has dominated the previous works on the PlantVillage dataset and achieved 99% and 99.69% accuracy on the Pepper dataset and PlantVillage datasets, respectively." @default.
- W3206899080 created "2021-10-25" @default.
- W3206899080 creator A5016610370 @default.
- W3206899080 creator A5031881955 @default.
- W3206899080 creator A5048952057 @default.
- W3206899080 creator A5065218877 @default.
- W3206899080 date "2021-01-01" @default.
- W3206899080 modified "2023-10-11" @default.
- W3206899080 title "Plant Disease Detection in Imbalanced Datasets Using Efficient Convolutional Neural Networks With Stepwise Transfer Learning" @default.
- W3206899080 cites W126301080 @default.
- W3206899080 cites W1564527624 @default.
- W3206899080 cites W1597793043 @default.
- W3206899080 cites W2117539524 @default.
- W3206899080 cites W2148143831 @default.
- W3206899080 cites W2165698076 @default.
- W3206899080 cites W2473156356 @default.
- W3206899080 cites W2548258044 @default.
- W3206899080 cites W2733343268 @default.
- W3206899080 cites W2789255992 @default.
- W3206899080 cites W2886201417 @default.
- W3206899080 cites W2889543275 @default.
- W3206899080 cites W2919115771 @default.
- W3206899080 cites W2923504698 @default.
- W3206899080 cites W2936503027 @default.
- W3206899080 cites W2957284115 @default.
- W3206899080 cites W2963820222 @default.
- W3206899080 cites W3088208717 @default.
- W3206899080 cites W3100931193 @default.
- W3206899080 doi "https://doi.org/10.1109/access.2021.3119655" @default.
- W3206899080 hasPublicationYear "2021" @default.
- W3206899080 type Work @default.
- W3206899080 sameAs 3206899080 @default.
- W3206899080 citedByCount "35" @default.
- W3206899080 countsByYear W32068990802021 @default.
- W3206899080 countsByYear W32068990802022 @default.
- W3206899080 countsByYear W32068990802023 @default.
- W3206899080 crossrefType "journal-article" @default.
- W3206899080 hasAuthorship W3206899080A5016610370 @default.
- W3206899080 hasAuthorship W3206899080A5031881955 @default.
- W3206899080 hasAuthorship W3206899080A5048952057 @default.
- W3206899080 hasAuthorship W3206899080A5065218877 @default.
- W3206899080 hasBestOaLocation W32068990801 @default.
- W3206899080 hasConcept C108583219 @default.
- W3206899080 hasConcept C119857082 @default.
- W3206899080 hasConcept C150899416 @default.
- W3206899080 hasConcept C153180895 @default.
- W3206899080 hasConcept C154945302 @default.
- W3206899080 hasConcept C22019652 @default.
- W3206899080 hasConcept C41008148 @default.
- W3206899080 hasConcept C50644808 @default.
- W3206899080 hasConcept C81363708 @default.
- W3206899080 hasConceptScore W3206899080C108583219 @default.
- W3206899080 hasConceptScore W3206899080C119857082 @default.
- W3206899080 hasConceptScore W3206899080C150899416 @default.
- W3206899080 hasConceptScore W3206899080C153180895 @default.
- W3206899080 hasConceptScore W3206899080C154945302 @default.
- W3206899080 hasConceptScore W3206899080C22019652 @default.
- W3206899080 hasConceptScore W3206899080C41008148 @default.
- W3206899080 hasConceptScore W3206899080C50644808 @default.
- W3206899080 hasConceptScore W3206899080C81363708 @default.
- W3206899080 hasFunder F4320322035 @default.
- W3206899080 hasFunder F4320322120 @default.
- W3206899080 hasLocation W32068990801 @default.
- W3206899080 hasLocation W32068990802 @default.
- W3206899080 hasOpenAccess W3206899080 @default.
- W3206899080 hasPrimaryLocation W32068990801 @default.
- W3206899080 hasRelatedWork W3099765033 @default.
- W3206899080 hasRelatedWork W3133861977 @default.
- W3206899080 hasRelatedWork W3167935049 @default.
- W3206899080 hasRelatedWork W3183901164 @default.
- W3206899080 hasRelatedWork W3192840557 @default.
- W3206899080 hasRelatedWork W3193565141 @default.
- W3206899080 hasRelatedWork W4206357785 @default.
- W3206899080 hasRelatedWork W4226493464 @default.
- W3206899080 hasRelatedWork W4281381188 @default.
- W3206899080 hasRelatedWork W4312417841 @default.
- W3206899080 hasVolume "9" @default.
- W3206899080 isParatext "false" @default.
- W3206899080 isRetracted "false" @default.
- W3206899080 magId "3206899080" @default.
- W3206899080 workType "article" @default.