A TRIZ-inspired bat algorithm for gene selection in cancer classification

Basit Öğe Kaydı
dc.authoridhttps://orcid.org/0000-0003-1980-1791en_US
dc.authoridhttps://orcid.org/0000-0002-1135-5750en_US
dc.authoridhttps://orcid.org/0000-0002-5326-7919en_US
dc.contributor.authorAl-Betar, Mohammed Azmi
dc.contributor.authorAlomari, Osama Ahmad
dc.contributor.authorAbu-Romman, Saeid M.
dc.date.accessioned2023-08-18T09:50:21Z
dc.date.available2023-08-18T09:50:21Z
dc.date.issued2020en_US
dc.departmentMühendislik ve Mimarlık Fakültesien_US
dc.description.abstractGene expression data are expected to make a great contribution in the producing of efficient cancer diagnosis and prognosis. Gene expression data are coded by large measured genes, and only of a few number of them carry precious information for different classes of samples. Recently, several researchers proposed gene selection methods based on metaheuristic algorithms for analysing and interpreting gene expression data. However, due to large number of selected genes with limited number of patient's samples and complex interaction between genes, many gene selection methods experienced challenges in order to approach the most relevant and reliable genes. Hence, in this paper, a hybrid filter/wrapper, called rMRMR-MBA is proposed for gene selection problem. In this method, robust Minimum Redundancy Maximum Relevancy (rMRMR) as filter to select the most promising genes and an modified bat algorithm (MBA) as search engine in wrapper approach is proposed to identify a small set of informative genes. The performance of the proposed method has been evaluated using ten gene expression datasets. For performance evaluation, MBA is evaluated by studying the convergence behaviour of MBA with and without TRIZ optimisation operators. For comparative evaluation, the results of the proposed rMRMR-MBA were compared against ten state-of-arts methods using the same datasets. The comparative study demonstrates that the proposed method produced better results in terms of classification accuracy and number of selected genes in two out of ten datasets and competitive results on the remaining datasets. In a nutshell, the proposed method is able to produce very promising results with high classification accuracy which can be considered a promising contribution for gene selection domain.en_US
dc.identifier.doi10.1016/j.ygeno.2019.09.015en_US
dc.identifier.endpage126en_US
dc.identifier.issn0888-7543
dc.identifier.issn1089-8646
dc.identifier.issue1en_US
dc.identifier.pmid31676302en_US
dc.identifier.scopus2-s2.0-85075329982en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage114en_US
dc.identifier.urihttps://hdl.handle.net/11363/5371
dc.identifier.urihttps://doi.org/
dc.identifier.volume112en_US
dc.identifier.wosWOS:000506628500013en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.institutionauthorAlomari, Osama Ahmad
dc.language.isoenen_US
dc.publisherACADEMIC PRESS INC ELSEVIER SCIENCE, 525 B ST, STE 1900, SAN DIEGO, CA 92101-4495en_US
dc.relation.ispartofGenomicsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subjectGene selectionen_US
dc.subjectBat-inspired algorithmen_US
dc.subjectOptimizationen_US
dc.subjectTRIZen_US
dc.subjectMRMRen_US
dc.subjectSVMen_US
dc.subjectClassificationen_US
dc.titleA TRIZ-inspired bat algorithm for gene selection in cancer classificationen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
Ä°sim:
1-s2.0-S0888754319303611-main.pdf
Boyut:
2.23 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale / Article
Ä°ndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ N/A ]
Ä°sim:
license.txt
Boyut:
1.56 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
Ä°ndir

Koleksiyon

Web of Science ve Scopus Atıf Dizinlerindeki Yayınlar
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu