Detection of Formalin Cob Fish using an Android-Based Naive Bayes Classifier Method based on Fish Eye Image
Keywords:
formalin, HSV, naive Bayes classifier, Android, tuna fishAbstract
Tuna is a popular fish among Indonesians, but formalin is frequently used as a preservative because the freshness of the fish does not last long. It is difficult for the community to distinguish between formalin and non-formalin fish due to the widespread distribution of formalin fish. The Center for Drug and Food Control (BBPOM) in Banjarmasin still requires samples to be taken to the laboratory to be tested for formalin content, which takes about a day to complete. It is believed that a technology that can identify formalin tuna would assist the community in solving this problem. The HSV technique was utilized in this study, which involved looking at the fish's eye colour and classifying them using the Naive Bayes Classifier method. Based on the testing conducted on the formalin tuna identification application based on fisheye pictures utilizing the Android-based Naive Bayes Classifier technique, it was determined that the test results had an accuracy of 80%.
References
C. Novia, “Kajian Kelayakan Teknis dan Finansial Produksi Nugget Jamur Tiram Putih ( Pleurotus ostreatus ) Rasa Ikan Tongkol ( Euthynus aletrates ) Skala Industri Kecil,” p. 1, 2011.
M. S. Milo, “Mutu Ikan Tongkol ( Euthynnus affinis C. ) Di Kabupaten Gunungkidul dan Sleman Daerah Istimewa Yogyakarta,” p. 1, 2013.
A. N. Alfian, “Implementasi Regresi Logistik Untuk Mendeteksi Ikan Berformalin Berbasis Android Berdasarkan Citra dan Sifat Fisik Ikan,” 2016.
B. I. Siahaan, “Pendeteksi Ikan Berformalin Melalui Citra Mata Menggunakan Metode Probabilistic Neural Network Berbasis Android,” p. 1, 2018.
F. M. Hadini, “Sistem Pendeteksi Ikan Bandeng ( Chanos chanos ) Berformalin Berbasis Android Berdasarkan Image Mata Menggunakan Metode Naive Bayes Classifier,” 2016.
Y. Agustyani, S. Setyaningsih dan A. Qur'ania, “Model Deteksi Kandungan Formalin Pada Ikan Dengan Citra Hue Saturation Values ( HSV ) Menggunakan K-Nearest Neighbor”.
A. Saleh, “Implementasi Metode Klasifikasi Naive Bayes Dalam Memprediksi Besarnya Penggunaan Listrik Rumah Tangga,” Citec Journal, pp. 209-212, 2015.
E. Prasetyo, Pengolahan Citra Digital dan Aplikasinya Menggunakan Matlab, Andi, 2011.
D. Putra, Pengolahan Citra Digital, Yogyakarta: ANDI, 2010.
R. Munir, Pengolahan Citra Digital, Bandung: Informatika Bandung, 2002.
S. Madenda, Pengolahan Citra dan Video Digital Teori, Aplikasi dan Pemrograman Menggunakan MATLAB, Erlangga, 2015.
A. K. Atmaja, “Aplikasi Asap Cair Redestilasi Pada Karakterisasi Kamabako Ikan Tongkol (Euthynus affinis) Ditinjau Dari Tingkat Keawetan dan Kesukaan Konsumen,” pp. 14-17, 2009.
D. Destari, “Kemunduran Mutu Ikan Tongkol ( Euthynnus affinis ) Segar Di Pasar Modern dan Tradisional Kota Pekanbaru,” 2017.
N. Hasnah, “Identifikasi Kandungan Formalin Pada ikan Asin Yang Dijual Di Kota Kendari Sulawesi Tenggara,” pp. 5-8, 2018.
G. F. Rohmi, W. B. Zulfikar dan Y. A. Gerhana, “Implementasi Citra Digital Berdasarkan Nilai HSV Untuk Mengidentifikasi Jenis Tanaman Mangga Menggunakan Algoritma K-Nearest Neighbor,” vol. 1, pp. 142-147, 2018.
D. Syahid, J. dan D. Nursantika, “Sistem Klasifikasi Jenis Tanaman Hias Daun Philodendron Menggunakan Metode K-Nearest Neighbor (KNN) Berdasarkan Nilai Hue, Saturation, Value (HSV),” vol. 1, 2016.
J. E. Istiyanto, Pemrograman Smart Phone Menggunakan SDK Android dan Hacking Android, Graha Ilmu, 2013.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Rudy Ansari, Yuslena Sari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
