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.

      Estimasi Kandungan Lignin pada Dedak Padi Menggunakan KNN dengan Praproses PCA Berdasarkan Citra Grayscale

      Thumbnail
      View/Open
      Cover (464.1Kb)
      Full Text (1.040Mb)
      Lampiran (915.1Kb)
      Date
      2023
      Author
      Ajasri, Maulidanisa
      Kustiyo, Aziz
      Metadata
      Show full item record
      Abstract
      Pemalsuan dedak padi yang telah tercampur sekam bisa menurunkan kualitas pakan. Pengujian kandungan sekam dapat diukur dari kandungan lignin melalui reaksi pewarnaan menggunakan larutan phloroglucinol. Warna merah yang semakin pekat menunjukkan semakin tinggi kandungan sekam pada dedak padi. Oleh karenanya, pada penelitian ini akan dilakukan estimasi kandungan lignin pada dedak padi yang telah diwarnai tersebut dengan ekstraksi fitur berbasis Principal Component Analysis (PCA) dengan metode klasifkasi K-Nearest Neighbor (KNN). Citra yang digunakan adalah citra grayscale yang diperoleh dari transformasi citra RGB. Penelitian ini menghasilkan akurasi prediksi tertinggi sebesar 77.27%.
       
      Counterfeiting of rice bran mixed with husks can reduce feed quality. The husk content test can be measured from the lignin content through a staining reaction using a phloroglucinol solution. The darker red color indicates the higher the husk content in the rice bran. Therefore, this study will estimate the lignin content of rice bran mixed with husks using feature extraction based on Principal Component Analysis (PCA) with the K-Nearest Neighbor (KNN) classification method. The image used is a grayscale image obtained from the RGB image transformation. This research resulted in the highest prediction accuracy of 77.27%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/115943
      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