• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Prediksi Pertumbuhan Tanaman Akuaponik Menggunakan Length Features Extraction dan Multiple Linear Regression

    View/Open
    Fulltext (2.328Mb)
    Date
    2021
    Author
    Tarigan, Fachry Muhamad Anantama
    Advisor(s)
    Siregar, Baihaqi
    Rahmat, Romi Fadillah
    Metadata
    Show full item record
    Abstract
    Analisis pertumbuhan tanaman akuaponik masih dievaluasi secara konvensional oleh pengamatan manusia, yang bisa memakan waktu lama dan merusak tanaman. Dengan demikian, pengamatan menggunakan pengolahan citra digital dapat berguna untuk analisis pertumbuhan tanaman karena tidak langsung menyentuh dan mengakibatkan kerusakan tanaman. Pengamatan ini bertujuan untuk memprediksi pertumbuhan tanaman akuaponik berdasarkan suhu air dan TDS (Total Dissolved Oxygen). Nilai yang akan prediksi yaitu lebar citra tanaman, tinggi citra tanaman, dan luas citra tanaman. Penerapan untuk memprediksi pertumbuhan tanaman akuaponik pada penelitian ini menggunakan algoritma multiple linear regression. Penelitian ini menggunakan data citra tanaman pakcoy, suhu air, dan TDS yang dikumpulkan selama 2 kali masa panen. Tahap-tahap yang dilakukan adalah (1) pengumpulan data citra tanaman, suhu air, dan TDS, (2) image pre-processing dari citra tanaman yang meliputi cropping dan gamma correction, (3) image segmentation dengan menggunakan metode thresholding, (4) ekstraksi ciri tanaman dengan menggunakan lengh feature extraction, (5) pembuatan model multiple linear regression, (6) menghasilkan output prediksi luas tanaman. Prediksi pertumbuhan tanaman akuaponik pada penelitian kali ini memiliki akurasi yang berbeda-beda didasari dengan hasil pengujian sebagai berikut: (a) kecocokan model untuk luas (length) citra tanaman sebesar 72,4%, (b) kecocokan model untuk lebar (width) citra tanaman sebesar 43,9%, (c) kecocokan model untuk tinggi (height) citra tanaman sebesar 27,4%.
     
    Aquaponic plant growth analysis is still being evaluated conventionally by human observations, which can take a long time and damage crops. Thus, observations using digital image processing can be useful for analyzing plant growth because they do not directly touch and cause plant damage. This observation aims to predict aquaponic plant growth based on water temperature and TDS (Total Dissolved Oxygen). The values to be predicted are the width of the image of the plant, the height of the image of the plant, and the area of the image of the plant. The multiple linear regression algorithm was used in this study. The data used in this study were pakcoy plant image data, water temperature, and TDS which were collected during 2 harvest periods. The steps taken are (1) collecting plant image data, water temperature, and TDS, (2) image pre-processing of plant images which include cropping and gamma correction, (3) image segmentation using thresholding, (4) extraction of plant features using length feature extraction, (5) multiple linear regression modeling, (6) output of plant area predictions. The prediction of aquaponic plant growth in this research has different accuracy based on the following test results: (a) the resulting incompatibility of the model for plant image‟s length is 72,4%, (b) for plant image‟s width is 43,9%, (c) for plant image‟s height is 27,4%.

    URI
    http://repositori.usu.ac.id/handle/123456789/43714
    Collections
    • Undergraduate Theses [800]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV