Diagnóstico temprano de enfermedades en cultivo de maíz mediante Redes Neuronales Convolucionales (RNC)
Manglar · 30.06.2026 · 23 (2) · 257-264
DOI: 10.57188/manglar.2026.024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Manglar, online erschienen am 30.06.2026. Verfasst von Marcelo Antonio Callao-Pimentel und 2 weiteren Autor:innen.
Abstract (Originalsprache)
This study develops an automated classification model based on Convolutional Neural Networks (CNN) to analyze images of maize plants. The main objective was to build a system capable of accurately identifying the condition of maize leaves, classifying them as healthy or affected by common diseases such as common rust and Cercospora leaf spot. The "Corn Disease Dataset" from Kaggle was used, dividing the images into training, validation, and testing sets. The model, built using TensorFlow and Keras, achieved an evaluation accuracy of 97.22%, demonstrating high effectiveness. Data augmentation techniques and image preprocessing were applied to enhance the model’s performance and generalization capability. The results show that CNNs are a powerful tool for the early diagnosis of crop diseases, contributing to improved agricultural productivity and promoting sustainable farming practices.
Zitieren
APA
Callao-Pimentel, M. A., Paredes-López, L. R., & Burgos-Saavedra, L. E. R. (2026). Diagnóstico temprano de enfermedades en cultivo de maíz mediante Redes Neuronales Convolucionales (RNC). Manglar, 23(2), 257-264. https://doi.org/10.57188/manglar.2026.024
Vancouver
Callao-Pimentel MA, Paredes-López LR, Burgos-Saavedra LER. Diagnóstico temprano de enfermedades en cultivo de maíz mediante Redes Neuronales Convolucionales (RNC). Manglar. 2026;23(2):257-264. doi:10.57188/manglar.2026.024
BibTeX
@article{CallaoPimentel2026,
author = {Callao-Pimentel, Marcelo Antonio and Paredes-López, Lilian Roxana and Burgos-Saavedra, Luis Enrique Ricardo},
title = {Diagnóstico temprano de enfermedades en cultivo de maíz mediante Redes Neuronales Convolucionales (RNC)},
journal = {Manglar},
year = {2026},
volume = {23},
number = {2},
pages = {257--264},
doi = {10.57188/manglar.2026.024}
}
EUVIMED