DETEKSI OTOMATIS KELAPA SAWIT MENGGUNAKAN JARINGAN SARAF TIRUAN BACKPROPAGATION DAN ZONING
Abstract
Abstract: The process of detecting oil palm manually is very difficult if the tree is too tall, so a system is needed that can detect based on color, the use of backpropagation artificial neural networks is able to detect the level of ripeness where in this study Detection of the level of ripeness of oil palm fruit using 40 image data with 20 training data and 20 test data, based on the test results, the accuracy based on color reached 85%, with 17 accurate data and 3 inaccurate data. Optimization of image recognition up to 85% is achieved by considering two things, namely the right classification method and selective and appropriate feature extraction.
Keywords: backpropagation, zoning, oil palm.
Abstrak: Proses untuk mendeteksi kelapa sawit secara manual sangat sulit dilakukan jika pohon sudah terlalu tinggi, sehingga diperlukan suatu sistem yang bisa mendeteksi berdasarkan warna, penggunaan jaringan saraf tiruan backpropagation mampu mendeteksi tingkat kematangan dimana pada penelitian ini Deteksi tingkat kematangan buah kelapa sawit dengan menggunakan data citra sebanyak 40 data dengan 20 data latih dan 20 data uji, berdasarkan pada hasil pengujian didapatkan akurasi berdasarkan warna mencapai 85%, dengan jumlah 17 data yang akurat dan 3 data yang tidak akurat. Optimalisasi pengenalan citra hingga 85 % dicapai dengan memperhatikan dua hal, yaitu metode klasifikasi yang tepat dan ekstraksi ciri yang selektif dan sesuai.
Kata kunci: backpropagation, zoning, kelapa sawit
Full Text:
PDFReferences
Regolinda Maneno, Budiman Baso, Patricia G. Manek 2023, Deteksi Tingkat Kematangan Buah Pinang Menggunakan Metode Support Vector Machine Berdasarkan Warna Dan Tekstur, Journal of Information and Technology Unimor (JITU)
Fanny j. Doringin, Ali A. S. Ramschie., 2022, Pemodelan Robot Pemetik Buah Kelapa Berbasis Mikrokontroler Arduino Uno, Jurnal Elektrik, [S.l.], v. 1, n. 1, p. 1-11, june 2022.
M. S. Mustafa1,Z. Husin1,W. K. Tan1,M. F. Mavi1,R. S. M. Farook. evelopment of automated hybrid intelligent system for herbs plant classification and early herbs plant disease detection. Neural Computing and Applications, Springer-Verlag London Ltd., part of Springer Nature 2019.
Jhuria, M., Kumar, A., dan Borse, R., 2013, Image Processing for Smart Farming :Detection of Disease and Fruit Grading, IEEE, Second International Conference on Image Information Processing ( ICIIP), 521-526.
Sitorus, M. L.F., E. N. Akoeb, R. Sembiring & M. A. Siregar, Peningkatan Produksi Crude Palm Oil Melalui Kriteria Matang Panen Tandan Buah Segar, Jurnal Ilmiah Magister Agribisnis, 2(1) 2020: 26-32,
H. Ishak, M. Shiddiq, R. H. Fitra, and N. Z. Yasmin,2019, Ripeness Level Classification of Oil Palm Fresh Fruit Bunch Using Laser I nduced Fluorescence Imaging,J.Aceh Phys. Soc., vol. 8, no. 3, pp. 84–89
Lily amelia kerangka pengembangan
model sistem sensor Tingkat kematangan buah sawit pada proses sterilisasi minyak sawit mentah forum ilmiah volume 8 nomer 1, januari 2011
E. L. I. Yani, “Pengantar Jaringan Syaraf Tiru n,” pp. 0–14, 2005.
J.Gómez-Sanchis,J.D.Martín-Guerrero, E. Soria-Olivas, M. Martínez-Sober, R. Magdalena-Benedito, and J.Blasco, “Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques,” Expert Syst. Appl., vol. 39, no. 1, pp. 780–785, 2012, doi: 1016/j.eswa.2011.07.073
Listhyani Dhianira Sarie, Dr. Ir. Bambang Hidayat, IPM, Building count detection by using google earth based on digital image processing, Bandung: Universitas Telkom.
Kartar, S., Renu, D. & Rajneesh, R. 2011.Handwritten Gurumukhi Character Recognition Using Zoning Density and Background Directional Distribution Features. International Journal of Computer Science and Information Technologies, 2011.
DOI: https://doi.org/10.54314/jssr.v8i1.2746
Article Metrics
Abstract view : 36 timesPDF - 16 times
Copyright (c) 2025 JOURNAL OF SCIENCE AND SOCIAL RESEARCH