Performance Comparison of Support Vector Machines,Random Forest and Artificial Neural Networks inBinary Classification: Descriptive Comparison Study

Basit Öğe Kaydı
dc.contributor.authorDırıcan, Emre
dc.contributor.authorAkkuş, Zeki
dc.date.accessioned2024-09-19T16:25:16Z
dc.date.available2024-09-19T16:25:16Z
dc.date.issued2021
dc.departmentHatay Mustafa Kemal Üniversitesien_US
dc.description.abstractObjective: In this study, it was aimed to find themethod with high classification success among the methods used inthe study by comparing the supervised machine learning methodsaccording to the classification performance. Material and Meth ods: In our study, both the real data set obtained from 302 patientswith invasive ductal carcinoma and 24 different data sets obtainedby simulation were used to compare the classification performanceof support vector machines, random forest and artificial neural net works. The success of classifications of the methods used wascompared according to the general accuracy, F-measure, Matthewscorrelation coefficient, area under the curve (AUC) and discrimi nant power in breast cancer data. In addition, the difference in train ing-test accuracy in the simulation data and the significance of thisdifference were also evaluated. Results: The highest survival classifi cation accuracy (80%) for the test set of stage III patients with inva sive ductal carcinoma was obtained from support vector machines(SVM) with the radial-based kernel. The highest values in other per formance metrics (F-measure=0.87, Matthews correlation coeffi cient=0.22, AUC=0.89 and discriminant power=0.52), and the mostsuccessful results in simulation data were generally obtained fromSVM. Conclusion: SVM had higher accuracy in both the real data setand simulation data than random forest and artificial neural networks.en_US
dc.identifier.doi10.5336/biostatic.2021-81105
dc.identifier.endpage251en_US
dc.identifier.issn1308-7894
dc.identifier.issn2146-8877
dc.identifier.issue3en_US
dc.identifier.startpage236en_US
dc.identifier.trdizinid503915en_US
dc.identifier.urihttps://doi.org/10.5336/biostatic.2021-81105
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/503915
dc.identifier.urihttps://hdl.handle.net/20.500.12483/16325
dc.identifier.volume13en_US
dc.indekslendigikaynakTR-Dizinen_US
dc.language.isoenen_US
dc.relation.ispartofTürkiye Klinikleri Biyoistatistik Dergisien_US
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.titlePerformance Comparison of Support Vector Machines,Random Forest and Artificial Neural Networks inBinary Classification: Descriptive Comparison Studyen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
16325.pdf
Boyut:
1.12 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu