Effect of instance selection algorithms on prediction error of numerical variables

 

Wedi'i Gadw mewn:
Manylion Llyfryddiaeth
Awduron: Solís, Martín, Muñoz-Alvarado , Erick
Fformat: artículo original
Statws:Versión publicada
Dyddiad Cyhoeddi:2024
Disgrifiad:The main objective of this study is to analyze the effect of instance selection (IS) algorithms on the prediction error in regression tasks with machine learning. Six algorithms were evaluated; four from literature and two are new variants of one of them. Different percentages and magnitudes of noise were added to the output variable of 52 datasets to evaluate the algorithms. The results show that not all IS algorithms are effective. RegENN and its variants improve the prediction error (RMSE) of the regression task in most datasets for high percentages and magnitudes of noise. However, when the magnitude and percentage of noise are lower, for example, 10%-10%, 50%-10%, or 10%-30%, there is no evidence of improvement in most datasets. Other results are presented to answer four new questions about the performance of the algorithms.
Gwlad:Portal de Revistas TEC
Sefydliad:Instituto Tecnológico de Costa Rica
Repositorio:Portal de Revistas TEC
Iaith:Español
OAI Identifier:oai:ojs.pkp.sfu.ca:article/6937
Mynediad Ar-lein:https://revistas.tec.ac.cr/index.php/tec_marcha/article/view/6937
Allweddair:Instance selection algorithms
regression task
machine learning
noise
Algoritmos de selección de instancias
tareas de regresión
aprendizaje automático
ruido