View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Mathematics
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Mathematics
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Klasifikasi Kesehatan Janin dengan Regresi Logistik Multinomial menggunakan Seleksi Variabel pada Analisis Komponen Utama

      Thumbnail
      View/Open
      Cover (685.9Kb)
      Fulltext (1.402Mb)
      Lampiran (648.9Kb)
      Date
      2024
      Author
      Al Ubaidah, Hafidz
      Ardana, Ngakan Komang Kutha
      Sumarno, Hadi
      Metadata
      Show full item record
      Abstract
      Alat kardiotokografi mengklasifikasikan kesehatan janin ibu hamil dengan 21 faktor ke dalam 3 klasifikasi kesehatan yaitu sehat, terjangkit, dan patologi. Analisis komponen utama digunakan untuk mereduksi dimensi data kesehatan janin ibu hamil tanpa kehilangan informasi penting di dalamnya. Keberadaan komponen utama membuat klasifikasi kurang efektif sehinga diperlukan seleksi variabel. Salah satu pendekatan seleksi variabel adalah pemilihan variabel berdasarkan nilai loading absolut. Sementara Regresi Logistik Multinomial digunakan untuk memodelkan klasifikasi kesehatan janin. Hasilnya diperoleh 6 komponen utama dan 6 variabel yang signifikan terhadap kesehatan janin yaitu gerakan janin, deselerasi parah, variabilitas jangka pendek abnormal, minimum histogram FHR, maksimum histogram FHR, dan kecenderungan histogram dengan hasil evaluasi model F1 score terboboti mencapai 0.78 dan AUC terboboti sebesar 0.87.
       
      Cardiotocography measurements classify the fetal health of pregnant women with 21 factors into 3 health classifications healthy, affected, and pathology. Principal Component Analysis is used to reduce the dimensionality of pregnant fetal health data without losing important information. The existence of principal components make the classification less effective so that variable selection is needed. One of the variable selection approaches is the selection of variables based on the absolute loading value on. Multinomial Logistic Regression was used to model the classification of fetal health. The results obtained 6 principal components and 6 variables that are significant to fetal health, namely fetal movement, severe deceleration, abnormal short term variability, minimum FHR histogram, maximum FHR histogram, and histogram tendency with the results of model evaluation F1 score weighted to 0.78 and AUC weighted to 0.87.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/158459
      Collections
      • UT - Mathematics [1487]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository