CONVOLUTIONAL NEURAL NETWORK PADA IDENTIFIKASI VARIAN TANAMAN ANGGUR MENGGUNAKAN RESNET-50

  • Muhammad Ali Nur Hidayat Mahasiswa PJJ Amikom Yogyakarta

Abstract

Identification of grape plant variants is very important, as an initial step to determine

the validity of planted grape seeds. Grape variants can be distinguished after the vine bears

fruit, but this method takes 8 months to 2 years from planting depending on the care taken. the

second fastest way is to look at the shape of the grape leaves, but this method can only be done

by people who are experts in recognizing the variants/types of grapes, while ordinary people

will find it difficult to tell the variants of the grapes from the shape of the leaves. This study will

use the CNN Restnet-50 method to identify grapevine variants based on grape leaf images.

There are 150 grape leaf image data used with 3 grape variants consisting of 50 Nizina leaves,

50 Jupiter leaves and 50 Isabella leaves. grape leaf image data resized in pixels, remove

background, data augmentation. The system produces a training accuracy rate of 86% while the

best validation accuracy is 91%.

References

[1] Xia, E.Q., Deng, G.F., Guo, Y.J. and Li, H.B. (2010) Biological Activities of
Polyphenols from Grapes. International Journal of Molecular Sciences, 11,
622-646. http://dx.doi.org/10.3390/ijms11020622
[2]D. Hidayat, “Klasifikasi Jenis Mangga Berdasarkan Bentuk Dan Tekstur Daun Menggunakan Metode Convolutional Neural Network (CNN),” INTECOMS, vol. 5, no. 1, pp. 98–103, Jun. 2022, doi: 10.31539/intecoms.v5i1.3401.
[3] P. Ilyas, “PENGENALAN TANAMAN CABAI DENGAN TEKNIK KLASIFIKASI MENGGUNAKAN METODE CNN.” Seminar Nasional Mahasiswa Ilmu Komputer dan Aplikasinya (SENAMIKA), Aug. 14, 2020
[4] Arief Saputro, “DEEP TRANSFER LEARNING DENGAN MODEL ARSITEKTUR VGG16 UNTUK KLASIFIKASI JENIS VARIETAS TANAMAN LENGKENG BERDASARKAN CITRA DAUN”, Jurnal Mahasiswa Teknik Informatika (JATI), 2022
[5] Deni Hidayat, 2022, KLASIFIKASI JENIS MANGGA BERDASARKAN BENTUK DAN TEKSTUR DAUN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK(CNN), Jurnal Informatika Upgris (JIU), Semarang.
[6] Y. Guo, S. Han, Y. Li, C. Zhang, and Y. Bai, “K-Nearest Neighbor combined with guided Title of manuscript is short and clear, implies research results (First Author) 10 ■ ISSN: 1978-1520 filter for hyperspectral image classification,” in International COnference On Identification, Information and Knowledge in the Internet of Things, 2018, pp. 159–165.
[7] Y. I. Kurniawan, E. Soviana, and I. Yuliana, “Merging Pearson Correlation and TAN-ELR algorithm in recommender system,” in AIP Conference Proceedings, 2018, vol. 1977, doi: 10.1063/1.5042998.
[8] M. Sridevi, S. Aishwarya, A. Nidheesha, and D. Bokadia, Anomaly Detection by Using CFS Subset and Neural Network with WEKA Tools. Springer Singapore.
[9] C. Low, “NSL-KDD Dataset,” 2015. https://github.com/defcom17/NSL_KDD (accessed Sep. 13, 2019).
[10] D. Handoko, “Sistem Pendukung Keputusan Seleksi Penentuan Penerima Beasiswa Dengan Metode Simple Additive Weighting (SAW),” Universitas Muhammadiyah Surakarta, 2016.
[11] T. A., R. M., S. V., and S. B., “Grapes Leaf Disease Detection using Convolutional Neural Network,” IJCA, vol. 178, no. 20, pp. 7–11, Jun. 2019, doi: 10.5120/ijca2019918982.
[12] S. Albawi, T. A. Mohammed, and S. Al Zawi, “Understanding of a convolutional neural network,” in Proceedings of 2017 International Conference on Engineering and Technology, ICET 2017, 2018, vol. 2018-Janua, pp. 1–6, doi: 10.1109/ICEngTechnol.2017.8308186.
[13] X. Ou et al., “Moving Object Detection Method via ResNet-18 with Encoder Decoder Structure in Complex Scenes,IEEE Access, vol. 7, pp. 108152–108160,2019, doi: 10.1109/ACCESS.2019.2931922.
[14] N. Nafi’iyah and J. Maknun, “CNN Architecture for Classifying Types of Mango Based on Leaf Images,” telematika., vol. 14, no. 2, pp. 112–121, Aug. 2021, doi: 10.35671/telematika.v14i2.1262.
Published
2023-09-06