Módulo de parametrización y prueba de algoritmos para aprendizaje de máquinas en línea/ fuera de línea para el análisis de trayectoria GPS
Fecha
2023-03
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad de Guayaquil. Facultad de Ciencias Matemáticas y Físicas. Carrera de Ingeniería en Sistemas Computacionales.
Resumen
El presente trabajo aborda el desarrollo y evaluación de un módulo para la parametrización y
prueba de algoritmos de aprendizaje de máquinas en línea/fuera de línea para el análisis de
trayectorias GPS. Los objetivos principales de esta investigación son el desarrollo de
herramientas que permitan a los usuarios experimentar con diferentes algoritmos de aprendizaje
de máquinas y evaluar su rendimiento en el análisis de trayectorias GPS, así como proporcionar
un módulo personalizable y adaptable que pueda ser ajustado a las necesidades específicas de
los usuarios. El marco teórico del proyecto se centra en los algoritmos de aprendizaje de
máquinas y sus aplicaciones en el análisis de trayectorias GPS. El módulo ha sido desarrollado
utilizando una combinación de lenguaje de programación Python y bibliotecas de código
abierto, y permite la personalización de parámetros y configuraciones para adaptarse a las
necesidades específicas de los usuarios. La importancia de este trabajo radica en la creciente
relevancia de la tecnología GPS en muchos campos, como el transporte, la logística y la
seguridad, y la necesidad de un análisis de trayectorias GPS preciso y eficiente. La metodología
utilizada en este trabajo incluye el desarrollo e implementación del módulo, la prueba y
evaluación de diferentes algoritmos de aprendizaje de máquinas utilizando datos de trayectorias
GPS del mundo real, Los resultados de los experimentos muestran que el módulo es capaz de
mejorar significativamente el rendimiento del análisis de trayectorias GPS, y que la selección
de algoritmos y configuraciones de parámetros apropiados es crucial para lograr resultados
óptimos.
This paper presents the development and evaluation of a module for the parameterization and testing of online/offline machine learning algorithms for GPS trajectory analysis. The main objectives of this research are to develop a set of tools that allow users to experiment with different machine learning algorithms and evaluate their performance in analyzing GPS trajectories, as well as to provide an adaptable module that suits the specific needs of the user. The theoretical framework of the project focuses on machine learning algorithms and their applications in the analysis of GPS trajectories. The module has been developed using a combination of the Python programming language and open-source libraries, and allows customization of parameters and settings to suit the specific needs of users. The importance of this work lies in the increasing relevance of GPS technology in many fields, such as transportation, logistics, and the need for accurate and efficient GPS trajectory analysis. This work can contribute to the development of more accurate and efficient GPS trajectory analysis tools, and serve as a solid foundation for future research in this field. The methodology used in this work includes the development and implementation of the module, the testing and evaluation of different machine learning algorithms using real-world GPS track data, and the analysis of the impact of parameter settings on the performance of these algorithms. The results of the experiments show that the module is capable of significantly improving the performance of GPS trajectory analysis. In conclusion, the development and evaluation of this module can contribute to the improvement of GPS technology and its applications in various fields. The customizable and adaptable nature of the module allows for a wide range of applications, and its successful implementation and evaluation using real-world data provide a solid foundation for further research and development in this field.
This paper presents the development and evaluation of a module for the parameterization and testing of online/offline machine learning algorithms for GPS trajectory analysis. The main objectives of this research are to develop a set of tools that allow users to experiment with different machine learning algorithms and evaluate their performance in analyzing GPS trajectories, as well as to provide an adaptable module that suits the specific needs of the user. The theoretical framework of the project focuses on machine learning algorithms and their applications in the analysis of GPS trajectories. The module has been developed using a combination of the Python programming language and open-source libraries, and allows customization of parameters and settings to suit the specific needs of users. The importance of this work lies in the increasing relevance of GPS technology in many fields, such as transportation, logistics, and the need for accurate and efficient GPS trajectory analysis. This work can contribute to the development of more accurate and efficient GPS trajectory analysis tools, and serve as a solid foundation for future research in this field. The methodology used in this work includes the development and implementation of the module, the testing and evaluation of different machine learning algorithms using real-world GPS track data, and the analysis of the impact of parameter settings on the performance of these algorithms. The results of the experiments show that the module is capable of significantly improving the performance of GPS trajectory analysis. In conclusion, the development and evaluation of this module can contribute to the improvement of GPS technology and its applications in various fields. The customizable and adaptable nature of the module allows for a wide range of applications, and its successful implementation and evaluation using real-world data provide a solid foundation for further research and development in this field.
Descripción
PDF
Palabras clave
TRAYECTORIAS GPS, APRENDIZAJES DE MÁQUINAS, PARAMETRIZACIÓN DE ALGORITMO, PRUEBA DE ALGORITMOS Y ANÁLISIS DE DATOS, GPS TRAJECTORIES, MACHINE LEARNING, ALGORITHM PARAMETERIZATION, ALGORITHM TEST AND ANALYSIS OF DATA