Artículos - Ingeniería en Sistemas de Información

Permanent URI for this collection

https://repositorio.utc.edu.ec/handle/123456789/12813

Browse

Browsing Artículos - Ingeniería en Sistemas de Información by Subject "DATASET"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Automatic prediction of growth and yield of legume plants using artificial intelligence models in a smart mobile application.
    (Ecuador: La Maná: Universidad Técnica de Cotopaxi; Extensión La Maná, Carrera de Sistemas de Información, 2025-10-06) Soledispa Vera, Henry Stalyn; Navarrete Cedeño, Angel Julian; Borja Cristian, Darwin; Luna Murillo, Ricardo Augusto
    This article presents the design, training, and validation of a smart mobile application for the automated prediction of growth and yield in legume plants, using supervised learning algorithms. Random forest and decision tree models were employed, trained on a multivariable dataset with 319 records and 67 quantitative and qualitative variables collected through IoT sensors and meteorological APIs. The decision tree model achieved a coefficient of determination of 0.76 for plant height and 0.87 for forage weight, surpassing the random forest model in accuracy, with R² values of 0.80 and 0.72, respectively. The application, developed in React Native and linked to a Django backend, allows the user to select the algorithm they wish to work with. Furthermore, the functional validation, carried out with 350 beneficiaries including farmers and students, showed a high level of acceptance: 91% positively rated the usability of the application, and 84% expressed intent for recurrent use. This proposal represents a significant contribution to the digital agriculture ecosystem, providing an accessible, accurate, and adaptable tool with potential for scalability and community adoption.
  • Thumbnail Image
    Item
    Prediction model for cacao production integrated into an offline mobile application: the impact of artificial intelligence on agricultural decision-making.
    (Ecuador: La Maná: Universidad Técnica de Cotopaxi; Extensión La Maná, Carrera de Sistemas de Información, 2025-10-08) Chuqui Alcivar, Dennis Brishith; Torres Jimenez, Alex Joel; Borja Borja, Cristian Darwin; Bajaña Zajia, Johnny Xavier
    Cacao production, a key economic pillar for numerous rural communities in Ecuador, faces structural challenges related to climate variability and limited digital connectivity. This study presents the development and implementation of a yield prediction model based on the XGBoost algorithm, integrated into an offline mobile application designed to operate in agricultural environments without internet access. The research followed the CRISP-DM methodology and included the analysis of 5584 observations collected from plots in La Maná (Cotopaxi), corresponding to three cacao genotypes. Variables were processed using cleaning, imputation, and normalization techniques. The predictive model, validated with standard metrics (MSE, RMSE) and an R² of 0.9399, demonstrated robust fit and high interpretability. Subsequently, the model was deployed in a mobile app developed with React Native. Field deployment showed response times under five seconds, compatibility with low-end devices, and high user acceptance. Participatory validation confirmed the practical usefulness of the tool for real-time agronomic decision-making. This work provides evidence of the value of AI tailored to rural contexts and proposes a replicable approach for other value chains under similar conditions.