CRIS

Permanent URI for this communityhttps://cris-udd.scimago.es/handle/123456789/1

Browse

Settings

Access type: UnknownSubject: search.filters.subject.Machine learning

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    VPD Monitoring with ESP32 and Flask API for Early Detection of Powdery Mildew in Rose Greenhouses
    (2026)
    Herrera, Vicente-D.
    In this study, a vapor pressure deficit (VPD) monitoring system was developed using an ESP32 and a Flask-based API for the early detection of powdery mildew in rose greenhouses. The research demonstrated that the integration of intelligent systems and real-time analysis of environmental conditions allows for the rapid identification of factors that favor the development of powdery mildew. The SVM model employed achieved high accuracy, with a classification accuracy rate of 96% in identifying conditions conducive to this disease, which is crucial for reducing unnecessary interventions and optimizing resource management in greenhouses. Additionally, the use of an API facilitates the integration of the system with other management platforms, enhancing data accessibility and decision-making. This approach promotes more responsible agricultural practices aligned with environmental sustainability. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
      1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Risk-Aware Fleet Management in Public Enterprises: A Machine Learning Approach Using Web-Scraped Data
    (2025)
    Tania Calle-Jimenez
    ;
    Flavio Ibujes-Calle
    ;
    Jadán Guerrero, Janio  
    ;
    Sandra Sanchez-Gordon
    In recent years, technological advancements, particularly in artificial intelligence and machine learning, have enabled the automation of tasks once thought impractical. However, many public sector organizations continue to rely on manual processes, especially in areas like vehicle fleet management, where critical operational data remains underutilized. This study addresses that gap by proposing a machine learning model aimed at improving vehicle fleet management in public enterprises. The model focuses on classifying drivers based on their risk levels, leveraging behavioral data, individual driver characteristics, and patterns of vehicle usage to provide actionable recommendations for fleet optimization. A key innovation of this work is the integration of web scraping techniques to automatically collect and update data related to drivers, vehicles, and fleet operations. This significantly reduces the dependency on manual data entry and supports the automation of processes such as vehicle registration validity control. The proposed system also includes the development of driver risk classification models, with results visualized through an interactive dashboard and geospatial map to facilitate strategic decision-making. This approach enhances the efficiency, transparency, and data-driven decision-making capabilities of public entities managing transportation assets. © 2025 IEEE.
      9
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Machine Learning Algorithm Selection for Predictive Maintenance in the Oil Industry
    (2024)
    Alexander Briceño-Ruiz
    ;
    López Vargas, Wilson  
    ;
    Jahel Riofrío-Vera
    ;
    Steven Paredes-Medina
    ;
    Lourdes Mejía-Ibarra
    One of the applications of artificial intelligence (AI) within the industry is machine learning (ML), a powerful tool to perform predictive maintenance on machinery, as it allows for predicting future failure scenarios through data analysis and avoiding accidents. Electric submersible pumps (ESPs) are critical in the oil industry, as they are used in the artificial lift technique for oil extraction, standing out for their extensive production volume at high depths. However, ESPs are prone to frequent failures. For this reason, this study aimed to compare the performance of three popular nondeterministic ML algorithms in Rstudio, Random Forest (RF), Extreme Gradient Boosting (XGB), and Adaptive Boosting (AB), to determine the best predictive maintenance strategies for an ESP. This paper uses an artificial and public domain dataset containing cycle reading information, machine operating variables such as voltage and pressure expressed in average and standard deviation, maintenance cycle information, and component errors. The results showed that when predicting machine failures with the test dataset, the RF algorithm presented a lower variance (2.31273e-8) and higher average accuracy (99.878%); XGB (variance 4.61843e-8 and average accuracy of 99.850%), and AB (variance 7.688043e-8 and average accuracy of 99.844%). An independent sample Welch’s t-test was performed, and a significant difference was found between the accuracy of the RF and that of the other algorithms. It is concluded that RF proved more suitable for predictive maintenance of an ESP with the dataset used.
      9