The influence of input data standardization method on prediction accuracy of artificial neural networks

被引：62
|
作者：
Anysz, Hubert [1 ]
Zbiciak, Artur [1 ]
Ibadov, Nabi [1 ]
机构：
[1] Warsaw Univ Technol, Fac Civil Engn, Armii Ludowej16, PL-00637 Warsaw, Poland
来源：
XXV POLISH - RUSSIAN - SLOVAK SEMINAR -THEORETICAL FOUNDATION OF CIVIL ENGINEERING | 2016年 / 153卷
关键词：
input data standardization; artificial neural networks ANN; building contracts completion date predicting;
D O I：
10.1016/j.proeng.2016.08.081
中图分类号：
TU [建筑科学];
学科分类号：
0813 ;
摘要：
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 applied. 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. (C) 2016 The Authors. Published by Elsevier Ltd.
引用
收藏
页码：66 / 70
页数：5
相关论文
共 50 条
  • [31] Improving prediction of aphid flights by temporal analysis of input data for an artificial neural network
    Worner, SP
    Lankin, GO
    Samarasinghe, S
    Teulon, DAJ
    NEW ZEALAND PLANT PROTECTION, VOL 55, 2002, 55 : 312 - 316
  • [32] Augmentation of limited input data using an artificial neural network method to improve the accuracy of water quality modeling in a large lake
    Kim, Jaeyoung
    Seo, Dongil
    Jang, Miyoung
    Kim, Jiyong
    Journal of Hydrology, 2021, 602
  • [33] Augmentation of limited input data using an artificial neural network method to improve the accuracy of water quality modeling in a large lake
    Kim, Jaeyoung
    Seo, Dongil
    Jang, Miyoung
    Kim, Jiyong
    JOURNAL OF HYDROLOGY, 2021, 602
  • [34] Accurate short-term wind speed prediction by exploiting diversity in input data using banks of artificial neural networks
    Salcedo-Sanz, Sancho
    Perez-Bellido, Angel M.
    Ortiz-Garcia, Emilio G.
    Portilla-Figueras, Antonio
    Prieto, Luis
    Correoso, Francisco
    NEUROCOMPUTING, 2009, 72 (4-6) : 1336 - 1341
  • [35] Improved diagnostic accuracy for myocardial perfusion imaging using artificial neural networks on different input variables including clinical and quantification data
    Rahmani, R.
    Niazi, P.
    Naseri, M.
    Neishabouri, M.
    Farzanefar, S.
    Eftekhari, M.
    Derakhshan, F.
    Mollazadeh, R.
    Meysami, A.
    Abbasi, M.
    REVISTA ESPANOLA DE MEDICINA NUCLEAR E IMAGEN MOLECULAR, 2019, 38 (05): : 275 - 279
  • [36] Determination of Input for Artificial Neural Networks for Flood Forecasting Using the Copula Entropy Method
    Chen, Lu
    Ye, Lei
    Singh, Vijay
    Zhou, Jianzhong
    Guo, Shenglian
    JOURNAL OF HYDROLOGIC ENGINEERING, 2014, 19 (11)
  • [37] Optimal Input Variables Disposition of Artificial Neural Networks Models for Enhancing Time Series Forecasting Accuracy
    Fogno Fotso, Hervice Romeo
    Aloyem Kaze, Claude Vidal
    Kenmoe, Germaine Djuidje
    APPLIED ARTIFICIAL INTELLIGENCE, 2020, 34 (11) : 792 - 815
  • [38] Verification of the Accuracy of Cervical Spinal Cord Injury Prognosis Prediction Using Clinical Data-Based Artificial Neural Networks
    Kishikawa, Jun
    Kobayakawa, Kazu
    Saiwai, Hirokazu
    Yokota, Kazuya
    Kubota, Kensuke
    Hayashi, Tetsuo
    Morishita, Yuichiro
    Masuda, Muneaki
    Sakai, Hiroaki
    Kawano, Osamu
    Nakashima, Yasuharu
    Maeda, Takeshi
    JOURNAL OF CLINICAL MEDICINE, 2024, 13 (01)
  • [39] Prediction of fracture frequency from wireline data with aid of artificial neural networks
    2000, Institution of Mining and Metallurgy (109):
  • [40] Stock Prediction and Analysis Using Intermittent Training Data With Artificial Neural Networks
    Srinivasan, N.
    Lakshmi, C.
    2017 INTERNATIONAL CONFERENCE ON INNOVATIONS IN INFORMATION, EMBEDDED AND COMMUNICATION SYSTEMS (ICIIECS), 2017,
12345