FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034939418> ?p ?o ?g. }

• W3034939418 endingPage "105557" @default.
• W3034939418 startingPage "105557" @default.
• W3034939418 abstract "Abstract Iron deficiency chlorosis (IDC) is a major yield-limiting factor for soybean production in the mid-western USA. The most practical solution in mitigating losses due to IDC is the development and characterization of IDC tolerant varieties. Leveraging the advanced technique of unmanned aircraft system (UAS) and the thriving deep learning methodology, a convolutional neural network (CNN) could be trained to assist breeders with IDC resistance selection. However, a known difficulty in IDC screening is that the symptoms often vary across diverse genetic backgrounds and spatial or temporal soil heterogeneities. A robust CNN model is desired to mitigate such difficulty. While high robustness usually relies on a sufficiently large labeled training data, the available labeled samples in most breeding programs are normally not enough. Under this limitation, it is critical to find an alternative way to train a robust model. The solution proposed in this study was to apply unsupervised pre-training on the unlabeled aerial images that are much easier to obtain by the UAS. Specifically, a convolutional autoencoder (CAE) was pre-trained on unlabeled sub-images clipped from aerial RGB images; then, the pre-trained weights were reused to initialize the CNN model that was trained on labeled plot-wise sub-images clipped from stitched RGB maps. To test the robustness of this CAE initialized model (CAE1-CNN), two baseline models were equally trained: the first was CAE2-CNN, where the CAE2 was pre-trained with three times of unlabeled data as that of CAE1, by adding wniter wheat and sorghum aerial images; the second was Ran-CNN where the CNN was randomly initialized. Three conditions were considered for testing model robustness: different soybean trials, field locations and vegetative growth stages. Results revealed that both the CAE1-CNN and the CAE2-CNN had relatively better robustness than the Ran-CNN model, i.e., higher R2 and lower RMSE values, especially on different soybean trials and growth stages, which proved that the unsupervised pre-training added gains to the model robustness across diverse trials and growth stages. Similar performances were found between the CAE1-CNN andthe CAE2-CNN model, suggesting that augmenting the unlabled data did not bring significant improvement to model robustness. Additionally, during robustness test on different soybean trials, the unsupervised pre-training seemly showed the potential of alleviating the required number of labeled training samples. These promising findings could contribute to the research on crop stresses by providing a potential path towards developing a robust system for classifying or predicting stress severities under more varied conditions." @default.
• W3034939418 created "2020-06-19" @default.
• W3034939418 creator A5000467024 @default.
• W3034939418 creator A5002697531 @default.
• W3034939418 creator A5043396581 @default.
• W3034939418 creator A5068713577 @default.
• W3034939418 date "2020-08-01" @default.
• W3034939418 modified "2023-10-17" @default.
• W3034939418 title "Improving model robustness for soybean iron deficiency chlorosis rating by unsupervised pre-training on unmanned aircraft system derived images" @default.
• W3034939418 cites W1462825729 @default.
• W3034939418 cites W1990895816 @default.
• W3034939418 cites W1993956081 @default.
• W3034939418 cites W2005016157 @default.
• W3034939418 cites W2010762039 @default.
• W3034939418 cites W2021010973 @default.
• W3034939418 cites W2025768430 @default.
• W3034939418 cites W2036211748 @default.
• W3034939418 cites W2040612493 @default.
• W3034939418 cites W2064636089 @default.
• W3034939418 cites W2068086367 @default.
• W3034939418 cites W2086159508 @default.
• W3034939418 cites W2091913822 @default.
• W3034939418 cites W2100495367 @default.
• W3034939418 cites W2136655611 @default.
• W3034939418 cites W2293915081 @default.
• W3034939418 cites W2321627895 @default.
• W3034939418 cites W2324044936 @default.
• W3034939418 cites W2325748482 @default.
• W3034939418 cites W2604496315 @default.
• W3034939418 cites W2610332124 @default.
• W3034939418 cites W2726456930 @default.
• W3034939418 cites W2746411854 @default.
• W3034939418 cites W2789436454 @default.
• W3034939418 cites W2799437918 @default.
• W3034939418 cites W2808943413 @default.
• W3034939418 cites W2888962714 @default.
• W3034939418 cites W2895547478 @default.
• W3034939418 cites W2898048752 @default.
• W3034939418 cites W2901137651 @default.
• W3034939418 cites W2912977378 @default.
• W3034939418 cites W2913585986 @default.
• W3034939418 cites W2922701384 @default.
• W3034939418 cites W2946240954 @default.
• W3034939418 cites W2962936819 @default.
• W3034939418 cites W2987372848 @default.
• W3034939418 cites W59938353 @default.
• W3034939418 doi "https://doi.org/10.1016/j.compag.2020.105557" @default.
• W3034939418 hasPublicationYear "2020" @default.
• W3034939418 type Work @default.
• W3034939418 sameAs 3034939418 @default.
• W3034939418 citedByCount "6" @default.
• W3034939418 countsByYear W30349394182022 @default.
• W3034939418 countsByYear W30349394182023 @default.
• W3034939418 crossrefType "journal-article" @default.
• W3034939418 hasAuthorship W3034939418A5000467024 @default.
• W3034939418 hasAuthorship W3034939418A5002697531 @default.
• W3034939418 hasAuthorship W3034939418A5043396581 @default.
• W3034939418 hasAuthorship W3034939418A5068713577 @default.
• W3034939418 hasBestOaLocation W30349394181 @default.
• W3034939418 hasConcept C104317684 @default.
• W3034939418 hasConcept C119857082 @default.
• W3034939418 hasConcept C127413603 @default.
• W3034939418 hasConcept C153294291 @default.
• W3034939418 hasConcept C154945302 @default.
• W3034939418 hasConcept C205649164 @default.
• W3034939418 hasConcept C2776411976 @default.
• W3034939418 hasConcept C2777211547 @default.
• W3034939418 hasConcept C31972630 @default.
• W3034939418 hasConcept C41008148 @default.
• W3034939418 hasConcept C44154836 @default.
• W3034939418 hasConcept C51632099 @default.
• W3034939418 hasConcept C55493867 @default.
• W3034939418 hasConcept C59822182 @default.
• W3034939418 hasConcept C63479239 @default.
• W3034939418 hasConcept C86803240 @default.
• W3034939418 hasConceptScore W3034939418C104317684 @default.
• W3034939418 hasConceptScore W3034939418C119857082 @default.
• W3034939418 hasConceptScore W3034939418C127413603 @default.
• W3034939418 hasConceptScore W3034939418C153294291 @default.
• W3034939418 hasConceptScore W3034939418C154945302 @default.
• W3034939418 hasConceptScore W3034939418C205649164 @default.
• W3034939418 hasConceptScore W3034939418C2776411976 @default.
• W3034939418 hasConceptScore W3034939418C2777211547 @default.
• W3034939418 hasConceptScore W3034939418C31972630 @default.
• W3034939418 hasConceptScore W3034939418C41008148 @default.
• W3034939418 hasConceptScore W3034939418C44154836 @default.
• W3034939418 hasConceptScore W3034939418C51632099 @default.
• W3034939418 hasConceptScore W3034939418C55493867 @default.
• W3034939418 hasConceptScore W3034939418C59822182 @default.
• W3034939418 hasConceptScore W3034939418C63479239 @default.
• W3034939418 hasConceptScore W3034939418C86803240 @default.
• W3034939418 hasFunder F4320306114 @default.
• W3034939418 hasFunder F4320310264 @default.
• W3034939418 hasLocation W30349394181 @default.
• W3034939418 hasOpenAccess W3034939418 @default.
• W3034939418 hasPrimaryLocation W30349394181 @default.
• W3034939418 hasRelatedWork W1831365897 @default.
• W3034939418 hasRelatedWork W2035976912 @default.

• next