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...
Saved in:
| Published in: | Nuclear engineering and technology Vol. 53; no. 12; pp. 3944 - 3951 |
|---|---|
| Main Author: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
01.12.2021
Elsevier 한국원자력학회 |
| Subjects: | |
| ISSN: | 1738-5733, 2234-358X |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | 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. |
|---|---|
| AbstractList | 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, inpresence of large number of FS techniques, are very tedious and time consuming task. In this study totackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology basedon the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neuralnetwork (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, theF-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniquesof 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 asthe 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 bereduced from n m to n 1. The proposed methodology gives a simple and practical approach for morereliable and more accurate estimation of the target parameters compared to the methods such as the useof synthetic dataset or trial and error methods KCI Citation Count: 0 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. |
| Author | Moshkbar-Bakhshayesh, Khalil |
| Author_xml | – sequence: 1 givenname: Khalil orcidid: 0000-0002-7973-6787 surname: Moshkbar-Bakhshayesh fullname: Moshkbar-Bakhshayesh, Khalil email: moshkbar@sharif.edu organization: Department of Energy Engineering, Sharif University of Technology, Azadi Ave., Tehran, Iran |
| BackLink | https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002776056$$DAccess content in National Research Foundation of Korea (NRF) |
| BookMark | eNp9kUFvEzEQhVeoSKSBH8DNVw4b7PWuvRGnqoISqSoVChI3y2uPEycbO4ydRvw2_lydBHHg0NNIT-97M5p3XV2FGKCq3jM6Y5SJj5tZgDxraMNmVMwop6-qSdPwtuZd__OqmjDJ-7qTnL-prlPaUCraVtJJ9We5BgIhwW4Ygej9HqM2a-IDMXG31-hTDOTo85rkYrT-CTABcaDzAYEkGMFkXywZzDr4XwdIxEUkkLLf6ezDijw8PiZSkvQOcoHJIZ3US5pzgBAyGUFjOMl6XEUs23aJRHc2OQBbl8ijRksCHFCPZeRjxO3b6rXTY4J3f-e0-vHl8_L2a33_7W5xe3NfGy5prhkXrbOtBdH17QCuabUbxOA472QRpaOd0dZxKjgThTDzTmjGe8vsXFou-bT6cMkN6NTWeBW1P89VVFtUN9-XCzXve9H2XfEuLl4b9UbtsXwBf5-BsxBxpTRmb0ZQlGknOyEM75vWzruBuZ5JO2huQdpy0LRilyyDMSUE9y-PUXVqXW1UeYU6ta6oUKX1wsj_GOOzPlWUUfvxRfLThYTyyicPqJLxEAxYj6Xkcr9_gX4Gnz3O0w |
| CitedBy_id | crossref_primary_10_1016_j_radphyschem_2023_111180 crossref_primary_10_1016_j_anucene_2022_109668 crossref_primary_10_1016_j_radphyschem_2025_113081 crossref_primary_10_1016_j_nucengdes_2024_113120 |
| Cites_doi | 10.1016/j.anucene.2019.107232 10.1016/j.anucene.2021.108222 10.1016/j.pnucene.2019.103100 10.1016/j.asoc.2015.01.035 10.1080/00031305.1990.10475752 10.1016/j.asoc.2013.09.018 10.1016/j.net.2016.11.001 10.1016/j.anucene.2020.107667 10.1016/j.net.2021.01.040 10.1109/TNS.2014.2346234 10.1016/S0149-1970(97)00109-1 10.1126/science.1087447 10.1109/23.489417 10.1162/neco.1996.8.7.1341 10.1371/journal.pone.0117988 |
| ContentType | Journal Article |
| Copyright | 2021 Korean Nuclear Society |
| Copyright_xml | – notice: 2021 Korean Nuclear Society |
| DBID | 6I. AAFTH AAYXX CITATION DOA ACYCR |
| DOI | 10.1016/j.net.2021.06.030 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals Korean Citation Index |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2234-358X |
| EndPage | 3951 |
| ExternalDocumentID | oai_kci_go_kr_ARTI_9886485 oai_doaj_org_article_01af7566c3824d95b1f817dba3de7ddf 10_1016_j_net_2021_06_030 S1738573321003776 |
| GroupedDBID | .UV 0R~ 0SF 123 4.4 457 5VS 6I. 9ZL AACTN AAEDW AAFTH AALRI AAXUO ABMAC ACGFS ACYCR ADBBV ADEZE AENEX AEXQZ AFTJW AGHFR AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ BCNDV EBS EJD FDB GROUPED_DOAJ IPNFZ JDI KQ8 KVFHK M41 NCXOZ O9- OK1 RIG ROL SSZ AAYWO AAYXX ACVFH ADCNI ADVLN AEUPX AFPUW AIGII AKBMS AKRWK AKYEP CITATION |
| ID | FETCH-LOGICAL-c370t-1364fd4de6584bef24afb6bf3357de67f05cadf306316370c956a138d1d97d373 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 6 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000697930900008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1738-5733 |
| IngestDate | Tue Nov 21 21:43:10 EST 2023 Fri Oct 03 12:29:44 EDT 2025 Wed Oct 29 21:31:02 EDT 2025 Tue Nov 18 21:45:47 EST 2025 Wed May 17 00:09:18 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 12 |
| Keywords | Heterogeneous ensemble Parameter estimation Combination technique Supervised learning algorithm Features selection technique |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c370t-1364fd4de6584bef24afb6bf3357de67f05cadf306316370c956a138d1d97d373 |
| ORCID | 0000-0002-7973-6787 |
| OpenAccessLink | https://doaj.org/article/01af7566c3824d95b1f817dba3de7ddf |
| PageCount | 8 |
| ParticipantIDs | nrf_kci_oai_kci_go_kr_ARTI_9886485 doaj_primary_oai_doaj_org_article_01af7566c3824d95b1f817dba3de7ddf crossref_primary_10_1016_j_net_2021_06_030 crossref_citationtrail_10_1016_j_net_2021_06_030 elsevier_sciencedirect_doi_10_1016_j_net_2021_06_030 |
| PublicationCentury | 2000 |
| PublicationDate | December 2021 2021-12-00 2021-12-01 2021-12 |
| PublicationDateYYYYMMDD | 2021-12-01 |
| PublicationDate_xml | – month: 12 year: 2021 text: December 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Nuclear engineering and technology |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V Elsevier 한국원자력학회 |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier – name: 한국원자력학회 |
| References | Moshkbar-Bakhshayesh, Ghofrani (bib5) 2014; 61 Xue, Zhang, Browne (bib10) 2014; 18 Stuart, Segal, Koller, Kim (bib19) 2003; 302 Caruana, Niculescu-Mizil (bib16) 2006 Moshkbar-Bakhshayesh (bib26) 2021; 156 Sammut, Webb (bib15) 2011 Okut (bib25) 2016 Moshkbar-Bakhshayesh (bib6) 2020; 139 Basu, Ho (bib18) 2006 Goldberger, Hinton, Roweis, Salakhutdinov (bib21) 2004; 17 Bolón-Canedo, Alonso-Betanzos (bib14) 2018 Mukhopadhyay, Chaudhuri (bib9) 1995; 42 Moshkbar-Bakhshayesh, Mohtashami (bib2) 2019; 117 Chok (bib20) 2010 Moshkbar-Bakhshayesh (bib23) 2019; 14 BNPP (bib27) 2003 Markowski, Markowski (bib22) 1990; 44 Uhrig, Hines (bib4) 2005; 37 Bolón-Canedo, Sánchez-Maroño, Alonso-Betanzos (bib17) 2015; 30 Park, An, Yoo, Na (bib1) 2021 Soufan, Kleftogiannis, Kalnis, Bajic (bib11) 2015; 10 Moshkbar-Bakhshayesh, Ghanbari, Ghofrani (bib12) 2020; 146 Uhrig, Tsoukalas (bib3) 1999; 34 Choi, Yoo, Back, Na (bib7) 2017; 49 Wolpert (bib13) 1996; 8 Fausett (bib8) 2006 Wang, Ji, Leung, Sum (bib24) 2009; 4 Bolón-Canedo (10.1016/j.net.2021.06.030_bib17) 2015; 30 Moshkbar-Bakhshayesh (10.1016/j.net.2021.06.030_bib6) 2020; 139 Chok (10.1016/j.net.2021.06.030_bib20) 2010 Mukhopadhyay (10.1016/j.net.2021.06.030_bib9) 1995; 42 Basu (10.1016/j.net.2021.06.030_bib18) 2006 Stuart (10.1016/j.net.2021.06.030_bib19) 2003; 302 Okut (10.1016/j.net.2021.06.030_bib25) 2016 Xue (10.1016/j.net.2021.06.030_bib10) 2014; 18 Moshkbar-Bakhshayesh (10.1016/j.net.2021.06.030_bib26) 2021; 156 Wang (10.1016/j.net.2021.06.030_bib24) 2009; 4 Moshkbar-Bakhshayesh (10.1016/j.net.2021.06.030_bib23) 2019; 14 BNPP (10.1016/j.net.2021.06.030_bib27) 2003 Moshkbar-Bakhshayesh (10.1016/j.net.2021.06.030_bib12) 2020; 146 Uhrig (10.1016/j.net.2021.06.030_bib4) 2005; 37 Goldberger (10.1016/j.net.2021.06.030_bib21) 2004; 17 Park (10.1016/j.net.2021.06.030_bib1) 2021 Soufan (10.1016/j.net.2021.06.030_bib11) 2015; 10 Choi (10.1016/j.net.2021.06.030_bib7) 2017; 49 Wolpert (10.1016/j.net.2021.06.030_bib13) 1996; 8 Fausett (10.1016/j.net.2021.06.030_bib8) 2006 Bolón-Canedo (10.1016/j.net.2021.06.030_bib14) 2018 Caruana (10.1016/j.net.2021.06.030_bib16) 2006 Moshkbar-Bakhshayesh (10.1016/j.net.2021.06.030_bib2) 2019; 117 Sammut (10.1016/j.net.2021.06.030_bib15) 2011 Moshkbar-Bakhshayesh (10.1016/j.net.2021.06.030_bib5) 2014; 61 Uhrig (10.1016/j.net.2021.06.030_bib3) 1999; 34 Markowski (10.1016/j.net.2021.06.030_bib22) 1990; 44 |
| References_xml | – volume: 156 year: 2021 ident: bib26 article-title: Identification of the appropriate architecture of multilayer feed-forward neural network for estimation of NPPs parameters using the GA in combination with the LM and the BR learning algorithms publication-title: Ann. Nucl. Energy – volume: 42 start-page: 2209 year: 1995 end-page: 2220 ident: bib9 article-title: A feature-based approach to monitor motor-operated valves used in nuclear power plants publication-title: IEEE Trans. Nucl. Sci. – volume: 18 start-page: 261 year: 2014 end-page: 276 ident: bib10 article-title: Particle swarm optimisation for feature selection in classification: novel initialisation and updating mechanisms publication-title: Appl. Soft Comput. – year: 2006 ident: bib18 article-title: Data Complexity in Pattern Recognition – year: 2010 ident: bib20 article-title: Pearson's versus Spearman's and Kendall's Correlation Coefficients for Continuous Data – volume: 4 start-page: 45 year: 2009 end-page: 48 ident: bib24 article-title: Regularization parameter selection for faulty neural networks publication-title: Int. J. Intell. Syst. Technol. – year: 2003 ident: bib27 article-title: Final safety analysis report (FSAR), Chapter 15, Rev. 0, – year: 2018 ident: bib14 article-title: Recent Advances in Ensembles for Feature Selection – year: 2021 ident: bib1 article-title: Leak flow prediction during loss of coolant accidents using deep fuzzy neural networks publication-title: Nuclear Engineering and Technology – volume: 146 year: 2020 ident: bib12 article-title: Development of a new features selection algorithm for estimation of NPPs operating parameters publication-title: Ann. Nucl. Energy – volume: 17 start-page: 513 year: 2004 end-page: 520 ident: bib21 article-title: Neighbourhood components analysis publication-title: Adv. Neural Inf. Process. Syst. – volume: 49 start-page: 495 year: 2017 end-page: 503 ident: bib7 article-title: Estimation of LOCA break size using cascaded fuzzy neural networks publication-title: Nuclear Engineering and Technology – year: 2016 ident: bib25 article-title: (Artificial Neural Networks-Models Applications) – year: 2006 ident: bib8 article-title: Fundamentals of Neural Networks: Architectures, Algorithms and Applications – volume: 34 start-page: 13 year: 1999 end-page: 75 ident: bib3 article-title: Soft computing technologies in nuclear engineering applications publication-title: Prog. Nucl. Energy – start-page: 161 year: 2006 end-page: 168 ident: bib16 article-title: An empirical comparison of supervised learning algorithms publication-title: Proceedings of the 23rd International Conference on Machine Learning – volume: 44 start-page: 322 year: 1990 end-page: 326 ident: bib22 article-title: Conditions for the effectiveness of a preliminary test of variance publication-title: Am. Statistician – volume: 30 start-page: 136 year: 2015 end-page: 150 ident: bib17 article-title: Distributed feature selection: an application to microarray data classification publication-title: Appl. Soft Comput. – volume: 117 year: 2019 ident: bib2 article-title: Classification of NPPs transients using change of representation technique: a hybrid of unsupervised MSOM and supervised SVM publication-title: Prog. Nucl. Energy – volume: 302 start-page: 249 year: 2003 end-page: 255 ident: bib19 article-title: A gene-coexpression network for global discovery of conserved genetic modules publication-title: Science – volume: 139 year: 2020 ident: bib6 article-title: Prediction of unmeasurable parameters of NPPs using different model-free methods based on cross-correlation detection of measurable/unmeasurable parameters: a comparative study publication-title: Ann. Nucl. Energy – volume: 10 year: 2015 ident: bib11 article-title: DWFS: a wrapper feature selection tool based on a parallel genetic algorithm publication-title: PloS One – volume: 8 start-page: 1341 year: 1996 end-page: 1390 ident: bib13 article-title: The lack of a priori distinctions between learning algorithms publication-title: Neural Comput. – year: 2011 ident: bib15 article-title: Encyclopedia of Machine Learning – volume: 37 start-page: 127 year: 2005 end-page: 138 ident: bib4 article-title: Computational intelligence in nuclear engineering publication-title: Nuclear Engineering and Technology – volume: 14 year: 2019 ident: bib23 article-title: Development of a modular system for estimating attenuation coefficient of gamma radiation: comparative study of different learning algorithms of cascade feed-forward neural network publication-title: J. Instrum. – volume: 61 start-page: 2636 year: 2014 end-page: 2642 ident: bib5 article-title: Development of a new method for forecasting future states of NPPs parameters in transients publication-title: IEEE Trans. Nucl. Sci. – volume: 139 year: 2020 ident: 10.1016/j.net.2021.06.030_bib6 article-title: Prediction of unmeasurable parameters of NPPs using different model-free methods based on cross-correlation detection of measurable/unmeasurable parameters: a comparative study publication-title: Ann. Nucl. Energy doi: 10.1016/j.anucene.2019.107232 – volume: 156 year: 2021 ident: 10.1016/j.net.2021.06.030_bib26 article-title: Identification of the appropriate architecture of multilayer feed-forward neural network for estimation of NPPs parameters using the GA in combination with the LM and the BR learning algorithms publication-title: Ann. Nucl. Energy doi: 10.1016/j.anucene.2021.108222 – start-page: 161 year: 2006 ident: 10.1016/j.net.2021.06.030_bib16 article-title: An empirical comparison of supervised learning algorithms – volume: 37 start-page: 127 issue: 2 year: 2005 ident: 10.1016/j.net.2021.06.030_bib4 article-title: Computational intelligence in nuclear engineering publication-title: Nuclear Engineering and Technology – year: 2006 ident: 10.1016/j.net.2021.06.030_bib18 – volume: 14 issue: 10 year: 2019 ident: 10.1016/j.net.2021.06.030_bib23 article-title: Development of a modular system for estimating attenuation coefficient of gamma radiation: comparative study of different learning algorithms of cascade feed-forward neural network publication-title: J. Instrum. – year: 2016 ident: 10.1016/j.net.2021.06.030_bib25 – volume: 117 year: 2019 ident: 10.1016/j.net.2021.06.030_bib2 article-title: Classification of NPPs transients using change of representation technique: a hybrid of unsupervised MSOM and supervised SVM publication-title: Prog. Nucl. Energy doi: 10.1016/j.pnucene.2019.103100 – volume: 30 start-page: 136 year: 2015 ident: 10.1016/j.net.2021.06.030_bib17 article-title: Distributed feature selection: an application to microarray data classification publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2015.01.035 – volume: 44 start-page: 322 issue: 4 year: 1990 ident: 10.1016/j.net.2021.06.030_bib22 article-title: Conditions for the effectiveness of a preliminary test of variance publication-title: Am. Statistician doi: 10.1080/00031305.1990.10475752 – year: 2011 ident: 10.1016/j.net.2021.06.030_bib15 – volume: 17 start-page: 513 year: 2004 ident: 10.1016/j.net.2021.06.030_bib21 article-title: Neighbourhood components analysis publication-title: Adv. Neural Inf. Process. Syst. – volume: 4 start-page: 45 issue: 1 year: 2009 ident: 10.1016/j.net.2021.06.030_bib24 article-title: Regularization parameter selection for faulty neural networks publication-title: Int. J. Intell. Syst. Technol. – volume: 18 start-page: 261 year: 2014 ident: 10.1016/j.net.2021.06.030_bib10 article-title: Particle swarm optimisation for feature selection in classification: novel initialisation and updating mechanisms publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2013.09.018 – volume: 49 start-page: 495 issue: 3 year: 2017 ident: 10.1016/j.net.2021.06.030_bib7 article-title: Estimation of LOCA break size using cascaded fuzzy neural networks publication-title: Nuclear Engineering and Technology doi: 10.1016/j.net.2016.11.001 – volume: 146 year: 2020 ident: 10.1016/j.net.2021.06.030_bib12 article-title: Development of a new features selection algorithm for estimation of NPPs operating parameters publication-title: Ann. Nucl. Energy doi: 10.1016/j.anucene.2020.107667 – year: 2018 ident: 10.1016/j.net.2021.06.030_bib14 – year: 2021 ident: 10.1016/j.net.2021.06.030_bib1 article-title: Leak flow prediction during loss of coolant accidents using deep fuzzy neural networks publication-title: Nuclear Engineering and Technology doi: 10.1016/j.net.2021.01.040 – year: 2003 ident: 10.1016/j.net.2021.06.030_bib27 – volume: 61 start-page: 2636 issue: 5 year: 2014 ident: 10.1016/j.net.2021.06.030_bib5 article-title: Development of a new method for forecasting future states of NPPs parameters in transients publication-title: IEEE Trans. Nucl. Sci. doi: 10.1109/TNS.2014.2346234 – year: 2010 ident: 10.1016/j.net.2021.06.030_bib20 – volume: 34 start-page: 13 issue: 1 year: 1999 ident: 10.1016/j.net.2021.06.030_bib3 article-title: Soft computing technologies in nuclear engineering applications publication-title: Prog. Nucl. Energy doi: 10.1016/S0149-1970(97)00109-1 – year: 2006 ident: 10.1016/j.net.2021.06.030_bib8 – volume: 302 start-page: 249 issue: 5643 year: 2003 ident: 10.1016/j.net.2021.06.030_bib19 article-title: A gene-coexpression network for global discovery of conserved genetic modules publication-title: Science doi: 10.1126/science.1087447 – volume: 42 start-page: 2209 issue: 6 year: 1995 ident: 10.1016/j.net.2021.06.030_bib9 article-title: A feature-based approach to monitor motor-operated valves used in nuclear power plants publication-title: IEEE Trans. Nucl. Sci. doi: 10.1109/23.489417 – volume: 8 start-page: 1341 issue: 7 year: 1996 ident: 10.1016/j.net.2021.06.030_bib13 article-title: The lack of a priori distinctions between learning algorithms publication-title: Neural Comput. doi: 10.1162/neco.1996.8.7.1341 – volume: 10 issue: 2 year: 2015 ident: 10.1016/j.net.2021.06.030_bib11 article-title: DWFS: a wrapper feature selection tool based on a parallel genetic algorithm publication-title: PloS One doi: 10.1371/journal.pone.0117988 |
| SSID | ssj0064470 |
| Score | 2.259466 |
| Snippet | Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover,... Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS)technique that outperforms other ones. Moreover,... |
| SourceID | nrf doaj crossref elsevier |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 3944 |
| SubjectTerms | Combination technique Features selection technique Heterogeneous ensemble Parameter estimation Supervised learning algorithm 원자력공학 |
| 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 |
| URI | https://dx.doi.org/10.1016/j.net.2021.06.030 https://doaj.org/article/01af7566c3824d95b1f817dba3de7ddf https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002776056 |
| Volume | 53 |
| WOSCitedRecordID | wos000697930900008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | Nuclear Engineering and Technology, 2021, 53(12), , pp.3944-3951 |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2234-358X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064470 issn: 1738-5733 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nj9MwELVgxQEOiE9RvjRCnJAi4tqOneMuYgWXqgeQ9mY5sR2VbdNVUvhz_Dlm7KQql-XCqVLk2m5nnHnTvL7H2HupJJ4aWRUq8qaQ3vOi8UoXbYymxowKSsdkNqFXK3N1Va9PrL6IE5blgfMX97HkLmrEHK0wS-lr1fBouPaNEz5o7yPdfUtdz81Uvgdjkdf5r5B4nEnxb36emZhd2PNjY7jkSbiT6M8nFSkJ9_9VmO72QzwpOZeP2MMJK8J53uNjdif0T9iDEwXBp-w3hhmwEw27ZhtgFgiHTQ_t0WAQ6LdWQKAHPpEwAsSQ5DxhTCY4GBk4SrmOgCgWSHqDoGzfwWq9HoEEwndEnBmBiPLdNFv2VjnAZD3Rgdt2-wFX242wj2lQxOpY4JREzgUSz8QP1Gfq-TP2_fLzt09fismPoWiFLsm1vpLRSx8ItTQhLqWLTdVEIZTGizqWqnU-YhMiEOXpssXey3FhPPe19kKL5-ys3_fhBQN6-Gt4WCrjSaDGOReNqwgtKNksa75g5RwT205i5eSZsbUzK-2Hxc1aCqMlZp4oF-zD8S03WanjtsEXFOjjQBLZThcw9eyUevZfqbdgck4TO-GVjENwqs1ta7_DlLLX7SYtS6_d3l4PFjuYr7Y2ppJGvfwfG3zF7tO6mX3zmp0dhp_hDbvX_jpsxuFtOjF_ANvSHng |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=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&rft.jtitle=Nuclear+engineering+and+technology&rft.au=Khalil+Moshkbar-Bakhshayesh&rft.date=2021-12-01&rft.pub=%ED%95%9C%EA%B5%AD%EC%9B%90%EC%9E%90%EB%A0%A5%ED%95%99%ED%9A%8C&rft.issn=1738-5733&rft.eissn=2234-358X&rft.spage=3944&rft.epage=3951&rft_id=info:doi/10.1016%2Fj.net.2021.06.030&rft.externalDBID=n%2Fa&rft.externalDocID=oai_kci_go_kr_ARTI_9886485 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1738-5733&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1738-5733&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1738-5733&client=summon |