Logotipo del repositorio
  • English
  • Español
  • Français
  • Português
  • Iniciar sesión
    ¿Has olvidado tu contraseña?
Logotipo del repositorio
  • Comunidades
  • Listar por
  • English
  • Español
  • Français
  • Português
  • Iniciar sesión
    ¿Has olvidado tu contraseña?
  1. Inicio
  2. Examinar por materia

Examinando por Materia "Aprendizaje automático"

Mostrando 1 - 20 de 44
Resultados por página
Opciones de ordenación
  • No hay miniatura disponible
    Ítem
    A Novel Ornstein Uhlenbeck Levy Model Conditioned on an Unknown Mean : Frecasting of the VIX
    (Universidad EAFIT, 2024) Aguirre Posada, Mario; Almonacid Hurtado, Paula María; Pérez Monsalve, Juan Pablo
  • No hay miniatura disponible
    Ítem
    A retail demand forecasting system of product groups characterized by time series based on “ensemble machine learning” techniques with feature enginnering
    (Universidad EAFIT, 2022) Mejía Chitiva, Santiago; Aguilar Castro, José Lisandro
  • No hay miniatura disponible
    Publicación
    Análisis comparativo de modelos predictivos para la estimación de PM2.5 : un enfoque basado en aprendizaje automático y predicción conformal
    (Universidad EAFIT, 2024) Camelo Valera, Matías; Martínez Vargas, Juan David; Sepúlveda Cano, Lina Maria
    Fine particulate matter (𝑃𝑀2.5pollution poses a significant environmental and public health challenge, requiring accurate predictive models for its monitoring and control. This study compares different machine learning approaches, including Linear Regression, Random Forest, and XGBoost, with and without the inclusion of mobility variables, to estimate 𝑃𝑀2.5 levels. Additionally, inductive conformal prediction is implemented to quantify uncertainty in the estimates and provide confidence intervals with 𝛼=0.05. The results show that while XGBoost experiences performance deterioration during training when mobility variables are included, it achieves the best validation performance with the lowest mean absolute error and the highest coefficient of determination. Conformal prediction enabled the establishment of confidence intervals with 89.26% coverage, close to the expected 95%, ensuring model reliability across different spatial and temporal scenarios. In conclusion, the use of machine learning models combined with advanced validation and calibration techniques, such as conformal prediction, enhances the accuracy and reliability of 𝑃𝑀2.5 estimation. However, the quality of input variables, particularly mobility-related data, remains a challenge, highlighting the need to incorporate meteorological information and improve data resolution. These findings contribute to the development of more reliable predictive tools for environmental management and air quality policy decision-making.
  • No hay miniatura disponible
    Ítem
    Análisis de los resultados de la aplicación del instrumento para la evaluación docente de la universidad EAFIT
    (Universidad EAFIT, 2024) Fernández Carmona, Laura Catalina; Guarín Zapata, Nicolás; Mola Ávila, José Antonio
  • No hay miniatura disponible
    Ítem
    Análisis de registros de mantenimiento de centrales de generación de energía con técnicas de procesamiento de lenguaje natural
    (Universidad EAFIT, 2024) Ocampo Davila, Andrés Alonso; Salazar Martínez, Carlos Andres
  • No hay miniatura disponible
    Ítem
    Aplicación de técnicas de aprendizaje automático para la proyección de la tasa de cambio entre COP y USD
    (Universidad EAFIT, 2022) Granada Carvajal, Lorena; Pérez Ramírez, Fredy Ocaris
  • No hay miniatura disponible
    Ítem
    Automatic Electrical Meter Forecasting : a Benchmarking Between Quantum Machine Learning and Classical Machine learning
    (Universidad EAFIT, 2024) Montes Castro, Jonathan Javier; Lalinde Pulido, Juan Guillermo; Sosa-Sierra, Daniel
    This work benchmarks Quantum Long Short-Term Memory (QLSTM) against classical LSTM networks using electrical meter data (KWh) from EPM, a public utility company, clients. The results show that QLSTM models learn in half the epochs compared to LSTM, as measured by the MSE cost function, while maintaining strong performance with respect to bias (Mean Absolute Percentage Error, MAPE) and variance (R^2) metrics. QLSTM leverages variational quantum circuits (VQC) to replace traditional LSTM cell gates, demonstrating the potential of quantum-hybrid algorithms in forecasting tasks. This study highlights the efficiency and accuracy advantages of quantum machine learning applied to real-world data from EPM’s electrical metering services.
  • No hay miniatura disponible
    Publicación
    Clasificación ABC de inventarios mediante modelos de aprendizaje por refuerzo
    (Universidad EAFIT, 2025) Arrieta Salgado, Karolina; Almonacid Hurtado, Paula María
  • No hay miniatura disponible
    Ítem
    Desarrollo de un sistema de apoyo a la toma de decisiones estilísticas en lenguaje de marca a través de una herramienta de machine learning
    (Universidad EAFIT, 2023) Córdoba García, Miguel de Germán; Maya Castaño, Jorge Hernán
  • No hay miniatura disponible
    Ítem
    Development of a machine learning-based methodology for an automatic control model in a Kaolin washing process
    (Universidad EAFIT, 2023) Contreras Buitrago, Oscar Javier; Martínez Vargas, Juan David
  • No hay miniatura disponible
    Publicación
    El impacto de las herramientas basadas en inteligencia artificial en la actividad profesional de las firmas legales, resultados de un mapeo sistemático de la literatura
    (Universidad EAFIT, 2025) Vásquez Mira, Juan Camilo; Suescún Monsalve, Elizabeth
  • No hay miniatura disponible
    Ítem
    En busca de un mayor bienestar en la ganadería de ceba y levante
    (2021-04-05) Martinez Guerrero, Christian Alexander; Christian Alexander Martinez-Guerrero; Garcia, Rodriguez; Aguilas Jose; Toro Mauricio; Pinto Angel; Rodriguez Paul; Vicerrectoría de Descubrimiento y Creación
  • No hay miniatura disponible
    Ítem
    Estimación de la distribución espacial del ingreso intra-urbano de Medellín y su área Metropolitana, usando imágenes satelitales diurnas
    (Universidad EAFIT, 2021) Salazar Vásquez, Jessica Patricia; Patiño Quinchía, Jorge Eduardo; Duque Cardona, Juan Carlos; Gómez Escobar, Jairo Alejandro
  • No hay miniatura disponible
    Ítem
    Estrategias de trading en acciones de BVC basadas en Machine Learning. ¿Precisión implica desempeño?
    (Universidad EAFIT, 2022) Cerro Espinal, Carlos Alberto; Agudelo Rueda, Diego Alonso
  • No hay miniatura disponible
    Ítem
    Evaluación de una red neuronal para la solución de ecuaciones diferenciales
    (Universidad EAFIT, 2023) Machado-Loaiza, José Manuel; Guarín-Zapata, Nicolás
  • No hay miniatura disponible
    Ítem
    Hacia un modelo predictivo que apoye el logro de KPI comerciales más asertivos : caso Empresa Comercializadora de Madera
    (Universidad EAFIT, 2023) Tavera Rodríguez, Jhon Walter; Tabares Betancur, Marta Silvia
  • No hay miniatura disponible
    Ítem
    Identificación de patrones socioeconómicos en Medellín a partir de imágenes satelitales
    (Universidad EAFIT, 2024) Ceballos Betancur, Mariana; Martínez Vargas, Juan David; Torres Madronero, María Constanza
  • No hay miniatura disponible
    Ítem
    Implementación de herramientas de apoyo en el proceso de decisión del Pricing y distribución comercial para los productos del activo bancario del segmento personas dentro de la banca minorista
    (Universidad EAFIT, 2023) Franco Amaya, Jair Fabian; Ardila Rodríguez, Jhon Sebastian; Rojas Ormaza, Brayan Ricardo
  • No hay miniatura disponible
    Ítem
    Inteligencia artificial para optimizar la producción de carne
    (Universidad EAFIT, 2020-12-01) Martinez Guerrero, Christian Alexander; Martinez-Guerrero, Christian Alexander; García, Rodrigo; Aguilar, Jose; Toro, Mauricio; Pinto, Angel; Rodríguez, Paul; GIDITIC
  • No hay miniatura disponible
    Ítem
    Intelligent model for monitoring, evaluating, and recommending strategies to improve the innovation processes of MSMEs
    (Universidad EAFIT, 2024) Gutiérrez Buitrago, Ana Gissel; Aguilar Castro, José Lisandro; Montoya Múnera, Edwin Nelson; Ortega Álvarez, Ana María
    The research focuses on how to improve the innovation process in micro, small and medium-sized enterprises (MSMEs). The study is framed within the Smart Innovation paradigm. In this context, innovation is considered a relevant factor for organizational performance that allows the creation and improvement of competitive advantages through the implementation of new ideas, products, concepts, and services to increase market positioning. For organizations aiming to enhance innovation performance, using intelligent systems and artificial intelligence to guide the innovation process poses a challenge. To address this problem, the goal was to develop methodologies, models and approaches to support decision-making related to the intelligent management of the innovation process. To achieve this, specific objectives were defined. The first one is to design an intelligent model to support innovation processes in MSMEs. The second objective is to apply Artificial Intelligence (AI) techniques to customer data sources in social networks and organizational data of MSMEs, aiming to enhance the innovation process; The third objective is to develop an intelligent system to evaluate the innovation levels in MSMEs. The fourth objective is to instantiate a case study in the fashion cluster of the department of Norte de Santander and in the national context, as part of the applied methodology. To fulfill these objectives, research articles were developed. The process began with a literature review article on the current challenges in applying AI techniques to improve innovation processes in MSMEs. A proposed innovation model was made based on the different innovation models that exist in the literature, and the four research articles were written in compliance with the scientific standards that accredit them, to meet the specific objectives outlined in this doctoral thesis. Each article evaluated the strategies/models using various data sets. The results demonstrated the capacity of the proposed methodologies and models for managing of innovation processes. For instance, the proposals enable the prediction of the level of innovation, and the definition of innovation problems, among other aspects, with positive results in performance metrics.
  • «
  • 1 (current)
  • 2
  • 3
  • »

Vigilada Mineducación

Universidad con Acreditación Institucional hasta 2026 - Resolución MEN 2158 de 2018

Software DSpace copyright © 2002-2025 LYRASIS

  • Configuración de cookies
  • Enviar Sugerencias