The Influence of Input Data Standardization Method on Prediction Accuracy of Artificial Neural Networks
Hubert Jerzy Anysz , Artur Zbiciak , Nabi Ibadov
AbstractAchieving good results in applying artificial neural networks (ANN) in predicting requires some preparatory works on the set of data. One of them is standardization which is necessary when nonlinear activation function is pplied. Basing on predicting completion period of building contracts by multi-layer ANN with error backpropagation algorithm, six different methods of input data standardization were checked in order to determine which allows to achieve the most accurate predictions.
|Journal series||Procedia Engineering, ISSN 1877-7058|
|Publication size in sheets||0.5|
|Conference||XXV Polish – Russian – Slovak Seminar “Theoretical Foundation of Civil Engineering", 11-07-2016 - 16-07-2016, Zilina, Słowacja|
|Keywords in English||input data standardization; artificial neural networks ANN; building contracts completion date predicting|
|Score|| = 15.0, 27-07-2020, ArticleFromJournalAndMatConfByConferenceseries|
= 15.0, 27-07-2020, ArticleFromJournalAndMatConfByConferenceseries
|Publication indicators||= 7; = 20; = 29.0|
|Citation count*||29 (2020-07-29)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.