The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural network
Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In thi...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-12-01
|
Series: | Nuclear Engineering and Technology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573321003776 |
id |
doaj-01af7566c3824d95b1f817dba3de7ddf |
---|---|
record_format |
Article |
spelling |
doaj-01af7566c3824d95b1f817dba3de7ddf2021-09-17T04:34:32ZengElsevierNuclear Engineering and Technology1738-57332021-12-01531239443951The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural networkKhalil Moshkbar-Bakhshayesh0Department of Energy Engineering, Sharif University of Technology, Azadi Ave., Tehran, IranSeveral reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods.http://www.sciencedirect.com/science/article/pii/S1738573321003776Combination techniqueFeatures selection techniqueHeterogeneous ensembleParameter estimationSupervised learning algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Khalil Moshkbar-Bakhshayesh |
spellingShingle |
Khalil Moshkbar-Bakhshayesh The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural network Nuclear Engineering and Technology Combination technique Features selection technique Heterogeneous ensemble Parameter estimation Supervised learning algorithm |
author_facet |
Khalil Moshkbar-Bakhshayesh |
author_sort |
Khalil Moshkbar-Bakhshayesh |
title |
The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural network |
title_short |
The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural network |
title_full |
The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural network |
title_fullStr |
The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural network |
title_full_unstemmed |
The ensemble approach in comparison with the diverse feature selection techniques for estimating NPPs parameters using the different learning algorithms of the feed-forward neural network |
title_sort |
ensemble approach in comparison with the diverse feature selection techniques for estimating npps parameters using the different learning algorithms of the feed-forward neural network |
publisher |
Elsevier |
series |
Nuclear Engineering and Technology |
issn |
1738-5733 |
publishDate |
2021-12-01 |
description |
Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods. |
topic |
Combination technique Features selection technique Heterogeneous ensemble Parameter estimation Supervised learning algorithm |
url |
http://www.sciencedirect.com/science/article/pii/S1738573321003776 |
work_keys_str_mv |
AT khalilmoshkbarbakhshayesh theensembleapproachincomparisonwiththediversefeatureselectiontechniquesforestimatingnppsparametersusingthedifferentlearningalgorithmsofthefeedforwardneuralnetwork AT khalilmoshkbarbakhshayesh ensembleapproachincomparisonwiththediversefeatureselectiontechniquesforestimatingnppsparametersusingthedifferentlearningalgorithmsofthefeedforwardneuralnetwork |
_version_ |
1717377699669868544 |