Please be advised that the site will be down for maintenance on Sunday, September 1, 2024, from 08:00 to 18:00, and again on Monday, September 2, 2024, from 08:00 to 09:00. We apologize for any inconvenience this may cause.
dc.contributor.author | Siddique, Aftab![]() |
|
dc.contributor.author | Cook, Kyla![]() |
|
dc.contributor.author | Holt, Yasmin![]() |
|
dc.contributor.author | anda, Sudhanshu S.![]() |
|
dc.contributor.author | Mahapatra, Ajit K.![]() |
|
dc.contributor.author | Morgan, Eric R.![]() |
|
dc.contributor.author | Van Wyk, Jan Aucamp![]() |
|
dc.contributor.author | Terrill, Thomas H.![]() |
|
dc.date.accessioned | 2024-08-01T09:21:43Z | |
dc.date.available | 2024-08-01T09:21:43Z | |
dc.date.issued | 2024-05 | |
dc.description | DATA AVAILABILITY STATEMENT : The data presented in this study are available on request from the corresponding author. | en_US |
dc.description.abstract | The increasing use of convolutional neural networks (CNNs) has brought about a significant transformation in numerous fields, such as image categorization and identification. In the development of a CNN model to classify images of sericea lespedeza [SL; Lespedeza cuneata (Dum-Cours) G. Don] from weed images, four architectures were explored: CNN model variant 1, CNN model variant 2, the Visual Geometry Group (VGG16) model, and ResNet50. CNN model variant 1 (batch normalization with adjusted dropout method) demonstrated 100% validation accuracy, while variant 2 (RMSprop optimization with adjusted learning rate) achieved 90.78% validation accuracy. Pre-trained models, like VGG16 and ResNet50, were also analyzed. In contrast, ResNet50’s steady learning pattern indicated the potential for better generalization. A detailed evaluation of these models revealed that variant 1 achieved a perfect score in precision, recall, and F1 score, indicating superior optimization and feature utilization. Variant 2 presented a balanced performance, with metrics between 86% and 93%. VGG16 mirrored the behavior of variant 2, both maintaining around 90% accuracy. In contrast, ResNet50’s results revealed a conservative approach for class 0 predictions. Overall, variant 1 stood out in performance, while both variant 2 and VGG16 showed balanced results. The reliability of CNN model variant 1 was highlighted by the significant accuracy percentages, suggesting potential for practical implementation in agriculture. In addition to the above, a smart- phone application for the identification of SL in a field-based trial showed promising results with an accuracy of 98–99%. The conclusion from the above is that a CNN model with batch normalization has the potential to play a crucial role in the future in redefining and optimizing the management of undesirable vegetation. | en_US |
dc.description.department | Veterinary Tropical Diseases | en_US |
dc.description.sdg | SDG-09: Industry, innovation and infrastructure | en_US |
dc.description.sdg | SDG-15:Life on land | en_US |
dc.description.sponsorship | The USDA-National Institute of Food and Agriculture. | en_US |
dc.description.uri | https://www.mdpi.com/journal/agronomy | en_US |
dc.identifier.citation | Siddique, A.; Cook, K.; Holt, Y.; Panda, S.S.; Mahapatra, A.K.; Morgan, E.R.; van Wyk, J.A.; Terrill, T.H. From Plants to Pixels: The Role of Artificial Intelligence in Identifying Sericea Lespedeza in Field-Based Studies. Agronomy 2024, 14, 992. https://doi.org/10.3390/agronomy14050992. | en_US |
dc.identifier.issn | 2073-4395 (online) | |
dc.identifier.other | 10.3390/agronomy14050992 | |
dc.identifier.uri | http://hdl.handle.net/2263/97391 | |
dc.language.iso | en | en_US |
dc.publisher | MDPI | en_US |
dc.rights | © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). | en_US |
dc.subject | Weight decay | en_US |
dc.subject | Learning rate | en_US |
dc.subject | Sericea lespedeza | en_US |
dc.subject | Convolutional neural network (CNN) | en_US |
dc.subject | SDG-09: Industry, innovation and infrastructure | en_US |
dc.subject | SDG-15: Life on land | en_US |
dc.title | From plants to pixels : the role of artificial intelligence in identifying Sericea lespedeza in field-based studies | en_US |
dc.type | Article | en_US |