Application of Artificial Intelligence in the Identification of Banana Bunch Top Virus (BBTV) in Mozambique
Résumé
Agricultural production faces many challenges, such as disease and pest infestation, which can lead to severe crop loss and environmental impacts due to the excessive use of chemicals. Artificial intelligence has become a key technique to solve different agricultural-related challenges. The main objective of this study was to train and validate artificial intelligence algorithms for the detection of Banana Bunchy Top Virus (BBTV) in banana crops. Approximately 2,500 images of healthy and BBTV-infected leaves were collected, stratified according to the stage of plant development, and used to calibrate and validate an artificial intelligence algorithm for the detection of BBTV. Pre-trained models such as VGG 16, ResNet50, and InceptionV3 were tested. The ResNet50 model achieved a training accuracy of 99.56% and validation precision, recall, and F1 score of 96.53%, 94.94%, and 95.73%, respectively, outperforming the other models in detecting BBTV-infected plants.
Citer ce document
Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)
Accès au document
Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter
Voir l'article sur le site de la revueLicence et provenance
Licence : CC BY
Notice moissonnée depuis OpenAlex le 28/09/2026. Le document reste hébergé par sa source.
Voir le document à la source →