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

      Pemodelan Klasifikasi Curah Hujan di Kabupaten Bogor Menggunakan Metode Random Forest

      Thumbnail
      View/Open
      Cover (731.2Kb)
      Fulltext (1.072Mb)
      Date
      2024
      Author
      Musthopic, Ade
      Afendi, Farit Mochamad
      Fitrianto, Anwar
      Metadata
      Show full item record
      Abstract
      ADE MUSTHOPIC. Pemodelan Klasifikasi Curah Hujan di Kabupaten Bogor Menggunakan Metode Random Forest. Dibimbing oleh FARIT MOCHAMAD AFENDI dan ANWAR FITRIANTO Kabupaten Bogor merupakan wilayah yang memiliki curah hujan cukup tinggi, dimana berdasarkan penelitian BMKG pada Februari 2021 menunjukan rata-rata curah hujan di Kabupaten Bogor berada di angka 300 mm/bulan. Tingginya curah hujan yang terus menerus dapat berdampak buruk dalam bidang pertanian, dan berpotensi terjadinya bencana alam. Penelitian ini bertujuan untuk melakukan klasifikasi terhadap curah hujan di Bogor dengan menggunakan komponen-komponen iklim sebagai variable pendukung menggunakan metode Random Forest. Kemudian dilakukan perbandingan kinerja model sebelum dan setelah dilakukannya penanganan data tidak seimbang dengan SMOTE. Sebelum dilakukannya SMOTE, nilai akurasi, sensitivitas, spesifisitas, skor F1 berturut-turut adalah 76%, 34%, 88%, and 40%. Sedangkan setelah dilakukan SMOTE nilai akurasi, sensitivitas, spesifisitas, skor F1 berturut-turut adalah 72%, 57%, 76%, and 49%. Dari data yang disimpulkan bahwa SMOTE tidak berpengaruh signifikan terhadap kinerja model klasifikasi. Kata Kunci : curah hujan, random forest, SMOTE
       
      Bogor is one of the district which have high rainfall level, based on BMKG research in February 2021 shows that average rainfall level in February is 300 mm/month. However, continuous high rainfall which have negative impact on agriculture, and also has the potential impact for natural disasters. This research is purposes to conducting rainfall classifications modelling in Bogor using climate component as supporting variable using random forest method. Then a comparison of model performance will be carried out before and after handling unbalaced data with SMOTE. The result obtained were that the model before SMOTE had accuracy, sensitivity, specificity, f1-score respectively 76%, 34%, 88%, and 40%. Whereas after SMOTE the accuracy, sensitivity, specificity, and f1-score respectively 72%, 57%, 76%, and 49%. Based on the result, it can be conclude that SMOTE has no significant effect on the performance of the classification model.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/155093
      Collections
      • UT - Statistics and Data Sciences [2260]

      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