Design and implementation of an artificial neural network to predict academic performance in Civil Engineering students from UNIFSLB

• Autores: Incio Flores, Fernando Alain, Capuñay Sanchez, Dulce Lucero, Estela Urbina, Ronald Omar, Delgado Soto, Jorge Antonio, Vergara Medrano, Segundo Edilberto
• Formato: artículo
• Fecha de Publicación: 2021
• Institución: Universidad Privada de Tacna
• Repositorio: Revistas - Universidad Privada de Tacna
• Lenguaje: español
• OAI Identifier: oai:revistas.upt.edu.pe:article/464
• Enlace del recurso: https://revistas.upt.edu.pe/ojs/index.php/vestsc/article/view/464
• Nivel de acceso: acceso abierto
• Materia: Rendimiento académico; red neuronal artificial; predicción; Academic performance; artificial neural network; prediction

Predicting the academic results of students allows the teacher to seek techniques and strategies at the indicated time during the teaching and learning process in order to improve the achievement of skills in their students. In this research, an artificial neural network (ANN) was implemented to predict the academic results of the physics course of the students of the II cycle of the Civil Engineering career of the National Intercultural University Fabiola Salazar Leguía de Bagua-Peru based on data historical. The RNA was designed and implemented in the MATLAB Software, its architecture is made up of an input layer, a hidden layer and an output layer, for the RNA training two algorithms that the MATLAB Toolbox has: the Scaled Conjugate Gradient achieving a prediction percentage of 70% and the Levenberg-Marquardt achieving a prediction percentage of 86%.