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.

      Deteksi Agroforestri Kakao dengan Algoritma Pohon Keputusan Pembelajar Mesin Menggunakan Citra Spot 7: Studi Kasus Kecamatan Malangke dan Malangke Barat, Luwu Utara

      Thumbnail
      View/Open
      Cover (470.6Kb)
      Full Teks (2.968Mb)
      Lampiran (1.001Mb)
      Date
      2023-09-26
      Author
      Ranti, Aulia
      Jaya, I Nengah Surati Jaya
      Metadata
      Show full item record
      Abstract
      Kajian ini mengulas tentang pembangunan teknik algoritma pohon keputusan dari pembelajar mesin (decision tree of machine learning) dengan fokus utama mengidentifikasi tanaman kakao agroforestri dan kakao monokultur. Tujuan utama dari penelitian ini adalah menemukan algoritma pohon keputusan terbaik untuk mendapatkan informasi sebaran spasial kakao agroforestri dan kakao monokultur. Penelitian ini menguji tiga kriteria pengambilan keputusan yaitu Information Gain, Gain Ratio, dan Gini Indeks menggunakan peubah-peubah spektral yang diturunkan dari SPOT 7 dan peubah-peubah geo-sosio biofisik. Kajian ini menemukan bahwa integrasi antara empat peubah spektral dan lima peubah geo-sosio biofisik menghasilkan performa model terbaik dengan overall accuracy (OA) 93,54%. Kajian ini menemukan bahwa kriteria terbaik dalam mendeteksi kakao adalah information gain dan citra sintetis NDVI menjadi peubah paling berpengaruh terhadap model. Kajian ini menemukan bahwa minimal producer’s dan user’s accuracy dari algoritma yang dihasilkan adalah 94,20% dan 93,76%.
       
      This study describes the development of the "decision tree of machine learning" algorithm development technique with the main focus on identifying agroforestry cocoa and monoculture cocoa plants. The main objective of this study is to find the best decision tree algorithm to obtain accurate spatial distribution of agroforestry and monoculture cacao. This study examined three criteria of the decision tree, namely the Information gain, the Gain ratio, and the Gini index algorithms, using spectral variables derived from SPOT 7 and bio-socio geophysics variables. This study found that integrating four spectral variables and five bio-socio-geophysics attributes resulted in the best model performance with an overall accuracy (OA) of 93,54%. This study found that the best criterion for detecting cocoa is information gain, and the NDVI was identified as the most influential attribute of the model. This study found that the minimum producer's and user's accuracy of the resulting algorithm is 94,20% and 93,76%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/125498
      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