Use of Trained Convolutional Neural Networks for Analysis of Symptoms Caused by Botrytis fabae Sard

Álvarez-Sánchez, David-E Y Arévalo, Anderson Y Benavides, Iván Felipe Y Salazar-Gonzalez, Claudia Y Betancourth, Carlos (2023) Use of Trained Convolutional Neural Networks for Analysis of Symptoms Caused by Botrytis fabae Sard. Revista de Ciencias Agrícolas, 40 (1). ISSN 2256-2273

Text 7854-Texto del artículo-36927-1-10-20230724.pdf Download (1MB)

Resumen

Home / Archives / Vol. 40 No. 1 (2023): Revista de Ciencias Agrícolas - January - april 2023 / Research Article Use of Trained Convolutional Neural Networks for Analysis of Symptoms Caused by Botrytis fabae Sard Authors David-E Álvarez-Sánchez Universidad de Nariño https://orcid.org/0000-0003-3563-2529 Anderson Arévalo Fundación Universitaria los Libertadores https://orcid.org/0000-0003-2574-4236 Iván Felipe Benavides Universidad de Nariño https://orcid.org/0000-0002-1139-3909 Claudia Salazar-González Universidad de Nariño https://orcid.org/0000-0002-5461-2761 Carlos Betancourth Universidad de Nariño https://orcid.org/0000-0001-6573-4230 DOI: https://doi.org/10.22267/rcia.20234001.198 Keywords: artificial intelligence, deep learning, Botrys fabae Sard, severity scale Abstract This study evaluated the use of convolutional neural networks (CNN) in agricultural disease recognition, specifically for Botrytis fabae symptoms. An experimental bean culture was used to capture images of healthy and affected leaflets, which were then used to perform binary classification and severity classification tests using several CNN models. The results showed that CNN models achieved high accuracy in binary classification, but performance decreased in severity classification due to the complexity of the task. InceptionResNet and ResNet101 were the models that performed best in this task. The study also utilized the Grad-CAM algorithm to identify the most significant B. fabae symptoms recognized by the CNNs. Overall, these findings can be used to develop a smart farming tool for crop production support and plant pathology research.

Tipo de Elemento:	Artículo
Palabras Clave:	artificial intelligence, deep learning, Botrys fabae Sard, severity scale
Asunto:	S Agricultura > S Agriculture (General)
Division:	Revistas > Revista de Ciencias Agrícolas
Depósito de Usuario:	FACIA Fac. Ciencias Agrícolas Udenar
Fecha Deposito:	30 Aug 2023 16:19
Ultima Modificación:	30 Aug 2023 16:19
URI:	http://sired.udenar.edu.co/id/eprint/9757

Ver Elemento