The Influence of Input Data Standardization Method on Prediction Accuracy of Artificial Neural Networks

Hubert Jerzy Anysz , Artur Zbiciak , Nabi Ibadov

Abstract

Achieving 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.
Author Hubert Jerzy Anysz (FCE / ICE)
Hubert Jerzy Anysz,,
- The Institute of Civil Engineering
, Artur Zbiciak (FCE / IRB)
Artur Zbiciak,,
- The Institute of Roads and Bridges
, Nabi Ibadov (FCE / ICE)
Nabi Ibadov,,
- The Institute of Civil Engineering
Journal seriesProcedia Engineering, ISSN 1877-7058, (0 pkt)
Issue year2016
Vol153
Pages66-70
Publication size in sheets0.5
ConferenceXXV 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
DOIDOI:10.1016/j.proeng.2016.08.081
Languageen angielski
File
Anysz H..pdf 123.42 KB
Score (nominal)15
Score sourceconferenceIndex
ScoreMinisterial score = 15.0, 29-10-2019, ArticleFromJournalAndMatConfByConferenceseries
Ministerial score (2013-2016) = 15.0, 29-10-2019, ArticleFromJournalAndMatConfByConferenceseries
Publication indicators WoS Citations = 7; Scopus Citations = 13
Citation count*18 (2019-12-08)
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?