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

      Perbandingan Metode Mesin Vektor Pendukung dan Peluang Maksimum dalam Mendeteksi Kerusakan dan Pertumbuhan Pasca Kebakaran Hutan dan Lahan: Studi Kasus di Jambi

      Thumbnail
      View/Open
      Cover (402.9Kb)
      Full text (2.355Mb)
      Attachment (298.2Kb)
      Date
      2023-02-01
      Author
      Prabowo, Christian Adi
      Jaya, I Nengah Surati
      Metadata
      Show full item record
      Abstract
      Studi ini meneliti tentang citra asli dan citra sintetik, yaitu citra komposit, citra Principal Component Analysis, dan citra indeks vegetasi menggunakan algoritma Mesin Vektor Pendukung (SVM) dan Peluang Maksimum (MLC) dalam mendeteksi kerusakan dan pertumbuhan akibat adanya kebakaran hutan dan lahan. Tujuan penelitian ini adalah mengetahui metode dan citra yang optimal untuk deteksi perubahan vegetasi setelah kebakaran. Pendekatan klasifikasi terbimbing digunakan untuk mengklasifikasikan setiap citra dengan algoritma SVM dan MLC. Citra komposit dengan algoritma MLC menghasilkan KA sebesar 76,7% sedangkan pada algoritma SVM sebesar 84,3%. Untuk citra sintetik, citra PCA dengan algoritma MLC menghasilkan KA sebesar 79,4%, sedangkan pada algoritma SVM sebesar 80,7%. Citra indeks vegetasi pada algoritma MLC menghasilkan KA sebesar 80,4%, sedangkan pada algoritma SVM sebesar 84,0%. Nilai akurasi citrakomposit dengan algoritma SVM merupakan yang terbaik.
       
      This study examined raw and synthetic images, i.e composite imagines, Principal Component Analysis imagines, and vegetation index imagines using Support Vector Machine (SVM) and Maximum Likelihood Classifier (MLC) algorithms in detecting damage and growth post-forest and land fires. The objective of this study was to find out the most optimal method and images for detecting vegetation changes after fires. The supervised classification approach was used to classify each imagery using the SVM and MLC algorithms. The raw images with the MLC algorithm provided a KA of 76,7% while the SVM algorithm was 84,3%. For synthetic images, the PCA images with the MLC algorithm produced a KA of 79,4%, while the SVM algorithm was 80,7%. The vegetation index images with the MLC algorithm produced a KA of 80,4%, while the SVM algorithm was 84,0%. The accuracy of composite imagery with the SVM algorithm was the highest.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/116537
      Collections
      • UT - Forest Management [3207]

      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