Din, Roshidi and Ku-Mahamud, Ku Ruhana
Prapemprosesan data menggunakan teknik tapisan dalam pemodelan perceptron multi aras.
Analisis, 8 (1&2).
This purpose of this research is to study the effect of filtering technique on house price modeling performance in predicting of learning capability of Multilayer Perceptron. This study also considered the comparison between neural network data testing modeling and multiple regression. Data is not only based on house price index but also includes other aspects which are related directly or indirectly to the house price index. From the finding, it is learnt that by using filtering technique, better prediction in house price modeling was obtained.
Actions (login required)