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

      Rancang Bangun Alat Deteksi Tingkat Kematangan Buah Belimbing Averrhoa carambola L. menggunakan Convolutional Neural Network yang Diintegrasikan dengan Raspberry Pi

      Thumbnail
      View/Open
      Cover (786.7Kb)
      Fullteks (2.123Mb)
      Lampiran (402.0Kb)
      Date
      2021
      Author
      Abdurrahman, Irfan
      Setiawan, Ardian Arif
      Zuhri, Mahfuddin
      Metadata
      Show full item record
      Abstract
      Belimbing merupakan hasil pertanian yang memiliki tingkat produksi yang tinggi, budidaya yang mudah, dan waktu kematangan yang relatif singkat. Petani umumnya mengklasifikasi tingkat kematangan buah biasanya masih dilakukan secara manual. Penelitian ini telah dibuat alat yang dapat menentukan tingkat kematangan buah belimbing secara presisi dan realtime. Convolutional Neural Network (CNN) digunakan untuk metode penentuan tingkat kematangan buah berdasarkan citra yang didapatkan. Tiap citra dilatih menggunakan tensorflow dengan model CNN yang berbeda, yaitu mobilenetV1, mobilenetV2, dan inceptionV3 dan diimplementasikan pada Raspberry Pi. Hasil pengujian alat menunjukkan model CNN mobilenetV1 memiliki akurasi sebesar 73.07% dengan kecepatan inferensi objek dalam waktu ±1150 milisekon. inceptionV3 sebesar 76.92% dengan kecepatan ±7000 milisekon, dan mobilenetV2 sebesar 61.54% dengan kecepatan ±900 milisekon.
       
      Starfruit is an agricultural product that has a high production rate, easy cultivation, and a relatively short maturity time. Farmers generally classify the level of fruit maturity manually. This research were produced a device that can determine the level of star fruit ripeness with precision and realtime. Convolutional Neural Network (CNN) is method that were used of determining the level of fruit maturity based on the image obtained. Each image was trained using tensorflow with a different CNN model, that is mobilenetV1, mobilenetV2, and inceptionV3 and implemented on the Raspberry Pi. The test results show that the CNN mobilenetV1 model has accuracy at 73.07% with the object inference velocity in ± 1150 milliseconds. InceptionV3 at 76.92% with inference in ±900 milliseconds , and mobilenetV2 at 61.54% with inference in ±7000 milliseconds.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/105837
      Collections
      • UT - Physics [1236]

      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