Loading...

Performance study of bayesian regularization based multilayer feed-forward neural network for estimation of the uranium price in comparison with the different supervised learning algorithms

Moshkbar Bakhshayesh, K ; Sharif University of Technology | 2020

738 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.pnucene.2020.103439
  3. Publisher: Elsevier Ltd , 2020
  4. Abstract:
  5. In this study, the estimation of the uranium price as one of the most important factors affecting the fuel cost of nuclear power plants (NPPs) is investigated. Supervised learning algorithms, especially, multilayer feed-forward neural network (FFNN) are used extensively for parameters estimation. Similar to other supervised methods, FFNN can suffer from overfitting (i.e. imbalance between memorization and generalization). In this study, different regularization techniques of FFNN are discussed and the most appropriate regularization technique (i.e. Bayesian regularization) is selected for estimation of the uranium price. The different methods including different learning algorithms of FFNN, support vector machine (SVM) with different kernel functions, radial basis network (RBN), and decision tree (DT) are utilized for the prediction of the uranium price and are compared with FFNN-BR. Average mean relative error (AMRE) and cumulative distribution function (CDF) of the results indicate that FFNN-BR method is more accurate for the uranium price estimation (i.e. CDF (0.0720) = 0.99 and AMRE = 0.0533). © 2020 Elsevier Ltd
  6. Keywords:
  7. Bayesian regularization ; Feed-forward neural network ; Generalization ; Supervised learning methods ; Uranium price estimation ; Cost estimating ; Decision trees ; Distribution functions ; Feed-forward neural networks ; Multilayer neural networks ; Multilayers ; Nuclear fuels ; Nuclear power plants ; Support vector machines ; Uranium ; Cumulative distribution function ; Mean relative error ; Multilayer feed forward neural networks ; Parameters estimation ; Radial basis networks ; Regularization technique ; Supervised methods ; Learning algorithms
  8. Source: Progress in Nuclear Energy ; Volume 127 , September , 2020
  9. URL: https://www.sciencedirect.com/science/article/abs/pii/S0149197020301918#!