Repository logo
  • English
  • Català
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Polski
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Yкраї́нська
  • Log In
    New user? Click here to register.Have you forgotten your password?
Repository logo
  • Communities & Collections
  • All of DSpace
  • English
  • Català
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Polski
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Yкраї́нська
  • Log In
    New user? Click here to register.Have you forgotten your password?
  1. Home
  2. Browse by Author

Browsing by Author "Vásquez Bernal Mario Xavier"

Now showing 1 - 1 of 1
Results Per Page
Sort Options
  • No Thumbnail Available
    Item
    Sistema predictivo de gestión integral de flotas y control de mantenimientos en la Cooperativa CIFA Internacional, Machala – Ecuador
    (Instituto Superior Tecnológico Particular Sudamericano, 2026) Vásquez Bernal Mario Xavier
    Introduction: the CIFA Internacional Transport Cooperative, in Machala, runs its bus fleet manually, with paper records and reactive maintenance that overlooks the data each vehicle produces while operating, which ends up causing unexpected failures and units left out of service. Objective: to develop a comprehensive predictive fleet management web system that brings together real time Internet of Things monitoring, artificial-intelligence-based failure prediction and automated maintenance control, in order to reduce operational downtime and improve unit availability. Methods: the study was applied, with a non-experimental descriptive-technological design and a mixed approach, and the development was organized into seven Scrum iterations. Telemetry was captured with a Teltonika FMC150 device and a CAN bus reading adapter, processed in a modular backend over a relational database, and anomaly detection was solved with the Isolation Forest algorithm. Results: the system was implemented and deployed in production, and validated with a pilot unit that transmitted more than forty-three thousand real telemetry readings. The model, trained on those data, identified eight deviations from normal behavior and indicated the anomalous parameter in each case, and the full flow from device to notification was verified. Conclusion: the feasibility of the solution was confirmed with real operating data, which lays the technological foundations to anticipate failures and reduce fleet downtime.

DSpace software copyright © 2002-2026 LYRASIS

  • Cookie settings
  • Privacy policy
  • End User Agreement
  • Send Feedback