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

      Penggunaan KNN Untuk Estimasi Lignin Dalam Dedak Padi Berbasis Citra Warna Dengan Praproses PCA

      Thumbnail
      View/Open
      Cover (453.2Kb)
      Fullteks (863.1Kb)
      Lampiran (1.135Mb)
      Date
      2023
      Author
      Sutrisno, Rijal Triadi Rijal Triadi
      Kustiyo, Aziz
      Metadata
      Show full item record
      Abstract
      Dedak padi pada umumnya digunakan sebagai bahan pakan tapi mengalami penurunan kualitas ketika dicampurkan dengan bahan lain seperti sekam untuk mendapatkan keuntungan lebih besar dengan memanfaatkan ketersediaan dedak sehingga kualitas dedak padi mengalami penurunan. Pemalsuan dapat diketahui melalui estimasi kandungan lignin dari proses reaksi pewarnaan. Penelitian ini dilakukan untuk mengestimasi kandungan lignin dari citra pewarnaan dedak padi berwarna model RGB dengan menggunakan metode ekstraksi fitur berbasis Principal Component Analysis (PCA) dan K-Nearest Neighbour (KNN) sebagai teknik klasifikasinya. Penelitian ini menghasilkan akurasi terbaik sebesar 77.27 % pada komponen warna merah.
       
      Rice bran is generally used as a feed ingredient but decreases in quality when mixed with other ingredients such as husks. to get greater profits by utilizing the availability of bran so that the quality of rice bran has decreased. Forgery can be determined by estimating the lignin content of the staining reaction process. This study was conducted to estimate the lignin content of the RGB model of rice bran coloring images using feature extraction methods based on Principal Component Analysis (PCA) and K-Nearest Neighbor (KNN) as classification techniques. This study resulted in the best accuracy of 77.27% on the red component.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/116044
      Collections
      • UT - Computer Science [2482]

      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