Deteksi Citra Ikan Nila dan Mujair Menggunakan Metode Jaringan Syaraf Tiruan Propagasi Balik

Smily Windharta Oei; Lailany Yahya; Ifan Wiranto

doi:10.55657/rmns.v2i1.85

Authors

Smily Windharta Oei Jurusan Matematika, Fakultas Matematika dan IPA, Universitas Negeri Gorontalo
Lailany Yahya Jurusan Matematika, Fakultas Matematika dan IPA, Universitas Negeri Gorontalo
Ifan Wiranto Jurusan Teknik Elektro, Fakultas Teknik, Universitas Negeri Gorontalo

DOI:

https://doi.org/10.55657/rmns.v2i1.85

Keywords:

Nile Tilapia, Mozambique Tilapia, Artificial Neural Network, Backpropagation, Convolution

Abstract

Nile Tilapia and Mozambique Tilapia fish are different, but from the same genus, Oreochromis, these two fish are closely related and have a similar appearance. Therefore, many buyers often find it difficult to distinguish them. This research employs one method in machine learning that is always use to classify image, called Backpropagation in Artificial Neural Network. There were two stages in this study, first was feature extraction using convolution. Second was the learning process using the backpropagation algorithm. Before classification, the image data were prepared by cropping to focus on the classified object. Then from the 254 images, they were divided into three groups, 140 image were for training data, 60 images were for validation data, and 54 were for testing data. The result conluded that the success rate and accuracy reached 74,07% from the total data. To conclude, this method had successfully applied.

Downloads

Download data is not yet available.

References

C. Cakra, S. Syarif, H. Gani, dan A. Patombongi, “Analisis Kesegaran Ikan Mujair Dan Ikan Nila Dengan Metode Convolutional Neural Network,” Simtek : jurnal sistem informasi dan teknik komputer, vol. 7, no. 2, hlm. 74–79, Agu 2022, doi: 10.51876/simtek.v7i2.138.

F. Aini, “Tingkat Konsumsi Ikan Nila Di Rumah Tangga Petani Kecamatan Sukaraja Kabupaten Sukabumi,” Journal of Agrifish, vol. 1, no. 3, Jul 2019.

E. Prasetyo, R. Purbaningtyas, R. D. Adityo, E. T. Prabowo, dan A. I. Ferdiansyah, “Perbandingan Convolution Neural Network Untuk Klasifikasi Kesegaran Ikan Bandeng Pada Citra Mata,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 3, hlm. 601, Jun 2021, doi: 10.25126/jtiik.2021834369.

R. T. Kreutzer dan M. Sirrenberg, Understanding Artificial Intelligence. Springer International Publishing, 2020.

A. Herdiansah, R. I. Borman, D. Nurnaningsih, A. A. J. Sinlae, dan R. R. al Hakim, “Klasifikasi Citra Daun Herbal Dengan Menggunakan Backpropagation Neural Networks Berdasarkan Ekstraksi Ciri Bentuk,” JURIKOM (Jurnal Riset Komputer), vol. 9, no. 2, hlm. 388, Apr 2022, doi: 10.30865/jurikom.v9i2.4066.

J. Jamaludin, C. Rozikin, dan A. S. Y. Irawan, “Klasifikasi Jenis Buah Mangga dengan Metode Backpropagation,” Techné : Jurnal Ilmiah Elektroteknika, vol. 20, no. 1, hlm. 1–12, Mar 2021, doi: 10.31358/techne.v20i1.231.

A. D. Putriana, D. S. Canta, E. L. Hadisaputro, dan N. Wahyuni, “Implementasi Backpropagation untuk Identifikasi Tanda Tangan Digital,” Jurnal Informatika dan Rekayasa Perangkat Lunak, vol. 4, no. 1, hlm. 11, Mar 2022, doi: 10.36499/jinrpl.v4i1.4996.

B. Zaman, “Komparasi Metode Klasifikasi Batik Menggunakan Neural Network Dan K-Nearest Neighbor Berbasis Ekstraksi Fitur Tekstur,” Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI), vol. 11, no. 1, hlm. 13, Apr 2022, doi: 10.23887/janapati.v11i1.41220.

T. M. Johan dan I. Rifna, “Identifikasi Kematangan Buah Tomat Berdasarkan Warna Menggunakan Metode Jaringan Syaraf Tiruan (Jst) Backpropagation,” Jurnal TIKA, vol. 7, no. 3, hlm. 309–315, Des 2022, doi: 10.51179/tika.v7i3.1647.

H. Honainah, F. F. Romadhoni, dan A. Ato’illah, “Klasifikasi Kesegaran Ikan Tongkol Berdasarkan Warna Mata Menggunakan Metode Backpropagation,” Jurnal Penelitian Inovatif, vol. 2, no. 2, hlm. 405–414, Agu 2022, doi: 10.54082/jupin.90.