Ciencias Agropecuarias

URI permanente para esta comunidadhttp://repositorio.uta.edu.ec/handle/123456789/870

Examinar

Filtros

20252

Ajustes

Tema: search.filters.subject.INTELIGENCIA ARTIFICIAL

Resultados de la búsqueda

Mostrando 1 - 2 de 2
  • Miniatura
    Item type:Ítem,
    Inteligencia artificial para la detección de dos enfermedades en manzana (Malus domestica, var. Emilia)
    (2025-08)
    Alomalisa Machado, Christian Ivan
    ;
    Muñoz Espinoza, Manolo Sebastián
    Early detection of diseases in agricultural crops is essential to ensure sustainable and profitable production. In this context, artificial intelligence (AI) has become a key tool for the development of automated plant health diagnosis systems. This thesis aims to develop an AI-based model for the detection of two common diseases in apple trees: powdery mildew (Podosphaera leucotricha) and apple scab (Venturia inaequalis), using digital images of leaves. To achieve this, a database of apple leaf images (cv. Emilia) was created, classified into three categories: healthy, with mildew, and with scab. The images were acquired, preprocessed, and annotated using the Roboflow platform. Subsequently, an object detection model based on YOLOv12 was trained to identify and visually locate affected areas in each image. The performance of the model was evaluated using metrics such as precision, sensitivity, and specificity, yielding promising results. The model showed optimal performance in identifying healthy leaves and those affected by scabs, along with a good balance between sensitivity and precision in detecting mildew. These findings demonstrate the feasibility of using deep learning models for the automated detection of foliar diseases in fruit trees. This study contributes to the development of accessible and scalable technological solutions for the efficient monitoring of diseases in apple crops, supporting informed decision-making in integrated pest and disease management.
  • Miniatura
    Item type:Ítem,
    Diseño de un modelo de Inteligencia artificial en la detección de Colletotrichum. spp y Oídium . spp en el cultivo de taxo (Passiflora mollisima B.H.K
    (2025-02)
    Aguilar Salan Edison David
    ;
    Munóz Espinosa Manolo Sebastián
    In this work, an Artificial Intelligence model based on the YOLOv11 architecture was developed for the segmentation and detection of three relevant classes in taxum (Passiflora mollisima B.H.K) culture: Colletotrichum spp., Oidium spp. and healthy leaves, in addition to the background class. A total of 1054 tagged images were used, of which 37 were used for testing and 40 for validation. The training took place over 60 eras. The results showed moderate precision (0.4994), recall (0.46815) and mAP@50 (0.38459) values, reflecting that the model manages to correctly identify about half of the positive instances, but presents confusions between classes with similar visual characteristics (in particular, healthy leaves and the background category). The confounding matrix corroborates these findings, evidencing the need to increase the diversity and quantity of training data, as well as to refine the model's hyperparameters to improve class discrimination. Despite the limitations, progressive decreases in loss curves during training and validation indicate a stable learning process. It is concluded that the model can perform a segmentation and initial detection of fungal diseases and healthy leaves, offering a valuable starting point for future improvements that contribute to a more efficient precision agriculture in taxo cultivation.