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.

      Pengembangan Sistem Identifikasi Spesies Burung yang Dilindungi Berbasis Citra menggunakan Convolutional Neural Network

      Thumbnail
      View/Open
      Cover (1.148Mb)
      Fullteks (2.388Mb)
      Lampiran (1.097Mb)
      Date
      2021
      Author
      Dhira, Dhana
      Hermadi, Irman
      Wulandari
      Metadata
      Show full item record
      Abstract
      Satwa yang dilindungi adalah satwa yang berpopulasi yang sedikit, jumlah individunya di alam menurun tajam, atau endemik. Demi menjaga kelestariannya, terdapat larangan atas tindakan memiliki, memelihara, atau memperniagakannya. Upaya pelestarian diawali oleh identifikasi. Pemerintah Republik Indonesia telah menetapkan 562 spesies burung yang dilindungi. Hal ini menjadi tantangan dalam identifikasi spesies burung. Penelitian ini bertujuan untuk mengembangkan aplikasi web yang menerapkan model convolutional neural network (CNN) untuk mengidentifikasi spesies burung yang dilindungi berbasis citra. Penelitian ini menggunakan citra dari sepuluh spesies burung yang dilindungi di Indonesia. Tahapan penelitian ini terdiri atas pengumpulan, praproses, dan pembagian data, pengembangan model CNN, evaluasi model, dan pengembangan web dengan metode Prototyping. Penelitian ini menghasilkan model dengan taraf akurasi 97%, precision 98%, dan recall 97% pada data uji. Aplikasi web dibangun dengan HTML, CSS, Javascript, dan library Tensorflow,js. Prototipe yang dikembangkan sudah dapat diterima berdasarkan hasil pengujian black-box.
       
      The protected animals are the animals that have small populations, a sharp decline in the number of individuals in the wild or endemic. The government has banned owning, keeping, or trading these animals. The first step of preserving these animals is identification. The government of the Republic of Indonesia has defined 562 bird species as the protected birds. This issue becomes a challenge on bird species identification. This study aims to develop a web application that implements a convolutional neural network (CNN) model for image-based protected bird species identification. This study uses the images of ten protected bird species in Indonesia as the research subject. This study consists of some stages: data collection, data preprocessing, data splitting, CNN model development, model evaluation, and web development using the Prototyping method. This study has successfully developed a model that gained 97% accuracy, 98% precision, and 97% recall on testing data. Web development uses HTML, CSS, Javascript, and Tensorflow.js. The black-box testing result shows that the prototype is acceptable.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/109513
      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