Mi DSpace
Usuario
Contraseña
Please use this identifier to cite or link to this item: http://hdl.handle.net/UCSP/15833
Title: Optimal selection of factors using Genetic Algorithms and Neural Networks for the prediction of students' academic
Authors: Echegaray Calderon, Omar
Barrios Aranibar, Dennis
Keywords: Algorithms;Artificial intelligence;Classification (of information);Forecasting;Genetic algorithms;Neural networks;Students;Academic performance;Fitness functions;Higher education;Optimal selection;Prediction accuracy;Education
Issue Date: 2016
Publisher: Institute of Electrical and Electronics Engineers Inc.
metadata.dc.relation.uri: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84969724235&doi=10.1109%2fLA-CCI.2015.7435976&partnerID=40&md5=5b7b5784e2450cbd46584f6056fdc254
Abstract: In this research, we propose to use a Genetic Algorithm with an Artificial Neural Network as fitness function in order to solve one of the most important problems in predicting academic success in higher education environments. Which is to find what are the factors that affect the students' academic performance. Also, using the same Artificial Neural Network as a predictor. To solve the problem, each individual of the genetic algorithm represents a group of factors, which will be evaluated with the fitness function seeking to obtain the optimal individual (group of factors) to predict academic performance. Then, with the same Artificial Neural Network we will classify students' academic grades in order to predict their semester final grades. With this technique, it was possible to reduce the initial amount of 39 factors (founded in the literature) to only 8. The prediction accuracy is 84.86%. © 2015 IEEE.
URI: http://repositorio.ucsp.edu.pe/handle/UCSP/15833
ISBN: 9781467384186
Appears in Collections:Artículos de investigación

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.