In this
study, we propose a decision support system for assessment of fetal well-being from
cardiotocogram data. The system is based on Principal Component Analysis and
Least Squares Support Vector Machines. Principal Component Analysis is used for
feature reduction of the cardiotocogram data set. Classification of the data
set with reduced features is made by using Least Squares Support Vector
Machines. Performance analysis of the proposed system is examined on the cardiotocogram
data set availabe on UCI Machine Learning Repository by using 10-fold Cross
Validation procedure. Experimetal results show that the proposed system has
98.74% classification accuracy, 98.86% sensitivity and 98.73% specificity rates
Cardiotocogram Decision support system Support vector machines Principal component analysis fetal well-being
Bu
çalışmada kardiotogram verisinden
fetal iyilik halinin belirlenmesi için bir karar destek sistemi önerilmiştir. Sistem En Küçük Kareler Destek Vektör
Makineleri ve Temel Bileşen Analizi üzerinde temellendirilmiştir. Temel Bileşen
Analizi yöntemi ile kardiotokogram veri kümesinin boyutu indirgenmiştir.
Özellik boyutu indirgenen veri kümesi üzerinde En Küçük Kareler Destek Vektör
Makineleri kullanılarak sınıflandırma işlemi gerçekleştirilmiştir. Önerilen
karar destek sisteminin başarımı UCI Makine Öğrenmesi Ambarlarından alınan kardiotokogram
veri kümesi üzerinde 10-katlı Çapraz Doğrulama tekniği kullanılarak
incelenmiştir. Deneysel sonuçlar önerilen sistemin %98,74 sınıflandırma
doğruluğuna, %98,86 duyarlılık oranına ve %98,73 özgüllük oranına sahip olduğunu
göstermiştir.
Kardiotokogram Karar destek sistemi Destek vektör makineleri Temel bileşen analizi Fetal iyilik hali
Subjects | Engineering |
---|---|
Journal Section | Research Articles |
Authors | |
Publication Date | December 16, 2016 |
Submission Date | March 18, 2016 |
Acceptance Date | November 27, 2016 |
Published in Issue | Year 2016 Volume: 21 Issue: 2 |
Announcements:
30.03.2021-Beginning with our April 2021 (26/1) issue, in accordance with the new criteria of TR-Dizin, the Declaration of Conflict of Interest and the Declaration of Author Contribution forms fulfilled and signed by all authors are required as well as the Copyright form during the initial submission of the manuscript. Furthermore two new sections, i.e. ‘Conflict of Interest’ and ‘Author Contribution’, should be added to the manuscript. Links of those forms that should be submitted with the initial manuscript can be found in our 'Author Guidelines' and 'Submission Procedure' pages. The manuscript template is also updated. For articles reviewed and accepted for publication in our 2021 and ongoing issues and for articles currently under review process, those forms should also be fulfilled, signed and uploaded to the system by authors.