Farley Albeiro Restrepo-Loaiza

Prof. Farley Albeiro Restrepo-Loaiza

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 June 2022
Verified
Book
Closed access
YÁYenny Alejandra Aguirre Álvarez
Yenny Alejandra Aguirre Álvarez
IHInstitución Universitaria Salazar Y Herrera
Institución Universitaria Salazar Y Herrera
MPMauricio Montoya Peláez
Mauricio Montoya Peláez
EBEmerson Andrés Giraldo Betancur
Emerson Andrés Giraldo Betancur
MVMauricio Gómez Vásquez
Mauricio Gómez Vásquez
UGUniversidad de Guanajuato
Universidad de Guanajuato
Las lúdicas se ocupan del desarrollo de actividades que propician motivación en cualquier área de conocimiento en cuanto que permiten el aprendizaje significativo a través del juego. Los estudiantes necesitan resolver problemas, analizar la realidad y transformarla, deben estar en capacidad de enfrentarse a situaciones en las que requieran tomar decisiones para resolver escenarios que aquejan a las organizaciones en el día a día. Con esta edición de Propuesta pedagógica para el aprendizaje de herramientas de productividad a través de lúdicas, útil para docentes, estudiantes e investigadores, la REDPROD busca documentar un trabajo de campo que divulga el diseño, desarrollo y evaluación de los procesos de experimentación en función de doce nuevas estratégicas pedagógicas. Dentro de los resultados se encuentran aprendizajes relacionados con la calidad, los sistemas productivos, los métodos y tiempos, las cartas de control estadístico, la logística, la simulación, las finanzas y los BMP, entre otros conceptos propios de la ingeniería industrial y afines en términos de productividad.

22 December 2020
Verified
Book
Closed access
JDJhobana Herrera Díaz
Jhobana Herrera Díaz
APAlejandro Díaz Peláez
Alejandro Díaz Peláez
CCChárol Kátherin Vélez Castañeda
Chárol Kátherin Vélez Castañeda
YCYesit Jovan Rodríguez Caro
Yesit Jovan Rodríguez Caro
FRFarley Albeiro Restrepo-Loaiza
Farley Albeiro Restrepo-Loaiza
JCJacobo Hernán Echavarría Cuervo
Jacobo Hernán Echavarría Cuervo

27 August 2025
Verified
Conference Paper
Closed access
FRFarley Albeiro Restrepo-Loaiza
Farley Albeiro Restrepo-Loaiza
JLJuan Carlos Briñez de Leoón
Juan Carlos Briñez de Leoón
IGIngry Natalia Gomez-Miranda
Ingry Natalia Gomez-Miranda
Conventional models often fall short in supporting decision-making from structured tabular data, as they struggle to capture complex feature interactions. At the same time, convolutional neural networks (CNNs), highly effective in computer vision, remain underutilized in this context. We propose a method to bridge this gap by transforming tabular records into fringe pattern images using Gaussian surface modeling. This visual encoding enables CNN-based classification and is evaluated across architectures such as ResNet, DenseNet, and GoogleNet. Our approach outperforms baseline models, highlighting the potential of visual representations to enhance structured data analysis across diverse applications.

23 December 2020
Verified
Book
Closed access
CQCarlos Alberto Lopera Quiroz
Carlos Alberto Lopera Quiroz
JMJuan Diego López Medina
Juan Diego López Medina
SQSofía Rojas Quintero
Sofía Rojas Quintero
SGSandra Milena Alvarez Gallo
Sandra Milena Alvarez Gallo
JVJorge Amado Rentería Vera
Jorge Amado Rentería Vera
FCFernando De Jesús Franco Cuartas
Fernando De Jesús Franco Cuartas

3 December 2025 in Computation
Verified
Journal Article
Open access
PDF file
JBJuan Carlos Briñez-De-Leon
Juan Carlos Briñez-De-Leon
AHAlejandra Estefanía Patiño Hoyos
Alejandra Estefanía Patiño Hoyos
FRFarley Albeiro Restrepo-Loaiza
Farley Albeiro Restrepo-Loaiza
Gabriel Cardona-OsorioGabriel Cardona-Osorio
Gabriel Cardona-Osorio
Academic dropout is a persistent challenge in higher education, particularly in contexts with socio-economic disparities and diverse learning conditions. Traditional predictive models often fail to capture the complex, non-linear interactions underlying student trajectories due to their reliance on low-dimensional and linear representations. This study introduces a visual representation–based computational approach for a student dropout analysis, applied to a real institutional dataset from Colombia. The methodology transforms structured student records into enriched visual encodings that map variable magnitudes, correlations, and latent relationships into spatial and textural patterns. These image-based representations allow convolutional neural networks (CNNs) to exploit hierarchical feature extraction, uncovering hidden dependencies not accessible through conventional classifiers. Experimental results demonstrate that a Convolutional Neural Network (CNN) trained from scratch outperforms both baseline machine learning models and transfer learning architectures across all evaluation metrics. Beyond predictive accuracy, the approach enhances data expressiveness, interpretability, and generalization, offering a visual-analytical perspective for understanding dropout dynamics. The Colombian case study confirms the feasibility and potential of this strategy in real educational settings, supporting early identification of at-risk students and contributing to the development of robust, explainable models in educational data mining and learning analytics.