Naslov
Identifying mathematical anxiety with MLP and RBF neural networks

Autori
Đurđević Babić, Ivana ; Milić, Tomislav ; Kozić, Ana

Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni

Knjiga
Mathematics education as a science and a profession

Urednik/ci
Kolar-Begović, Zdenka ; Kolar-Šuper, Ružica ; Jukić Matić, Ljerka

Izdavač
Element ; Fakultet za odgojne i obrazovne znanosti Sveučilišta Josipa Jurja Strossmayera u Osijeku ; Odjel za matematiku Sveučilišta Josipa Jurja Strossmayera u Osijeku

Grad
Zagreb

Godina
2017

Raspon stranica
250-257

ISBN
978-953-197-592-6

Ključne riječi
mathematical anxiety, physical activity, neural network, MLP, RBF

Sažetak
This research addresses the problem of mathematical anxiety which is usually associated with inadequate mathematical performance and achievement. It aims to develop neural network model for classification of students according to the degree of mathematical anxiety in order to examine and better understand the relationship and effects of physical activity along with some other factors on mathematical anxiety. For this purpose, Multilayer Perceptron (MLP) and Radial Basis Function (RBF) neural networks were used. The results of this research showed that neural network models were efficient in identifying students’ mathematical anxiety. With the purpose of exploring the relationships between the mathematical anxiety and input variables, sensitivity analysis was conducted and reported for the model with the highest overall classification accuracy.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Informacijske i komunikacijske znanosti

POVEZANOST RADA