Perancangan Sistem Klasifikasi Kesegaran Ikan Osphronemus Gouramy Menggunakan Imaging System Dengan Sumber Cahaya UV Dan Algoritma Deep Neural Network

Azizah, Nafil Nur (2023) Perancangan Sistem Klasifikasi Kesegaran Ikan Osphronemus Gouramy Menggunakan Imaging System Dengan Sumber Cahaya UV Dan Algoritma Deep Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 02311940000131-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2025. Download (5MB) | Request a copy

Abstract

Daging ikan merupakan salah satu sumber makanan yang banyak dikonsumsi manusia karena kaya akan manfaat tinggi protein, rendah lemak, dan terdapat beberapa vitamin dan mineral. Kesegaran ikan merupakan salah satu hal utama pada konsumen. Total Volatile Base Nitrogen (TVBN) suatu parameter yang dapat mengindikasikan kesegaran ikan. Perubahan warna berdampak langsung pada kesegaran ikan menurut SNI 2729:2013 menunjukkan tata cara pemeriksaan kesegaran secara konvensional. Imaging system dengan sinar UV telah diimplementasikan untuk menguantifikasi kesegaran ikan melalui warna permukaan sisik ikan. Ruang warna yang digunakan berupa RGB, HSV, LAB dengan empat momen warna yaitu mean, standar deviasi, skewness, kurtosis. Klasifikasi kesegaran ikan pada imaging system dengan sumber cahaya UV dan parameter kesegaran TVBN algoritma dengan Deep Neural Network. Hasil dari sistem klasifikasi kesegaran ikan memiliki akurasi keseluruhan sebesar 99.62%, sensitivitas rata-rata pada kelas sebesar 99.67%, presisi rata-rata pada kelas sebesar 99.33%.
========================================================================================================================
Fish meat is a food source that is widely consumed by humans because it is rich in the benefits of high protein, low fat, and contains several vitamins and minerals. Fish freshness is one of the main concerns of consumers. Total Volatile Base Nitrogen (TVBN) is a parameter that can indicate the freshness of fish. Changes in color and texture have a direct impact on the freshness of fish according to SNI 2729: 2013 shows the procedure for conventional freshness inspection. Imaging system equipped with UV light has been implemented to predict fish freshness by the surface color. The color space used is RGB, HSV, LAB with four color moments namely mean, standard deviation, skewness, kurtosis. Fish freshness classification on imaging system combines UV light source and TVBN freshness parameter algorithm with Deep Neural Network. The results of the fish freshness classification system have an overall accuracy of 99.62%, an average sensitivity in class of 99.67%, an average precision in class of 99.33%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Daging ikan, Deep Neural Network, Ruang Warna, Sinar UV, Total Volatil Base Nitrogen Color Spaces, Deep Neural Network, Fish meat, UV light source, Total Volatile Base Nitrogen
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QC Physics > QC475 Photoluminescence R Medicine > R Medicine (General) > R858 Deep Learning T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Nafil Nur Azizah
Date Deposited:	04 Aug 2023 04:21
Last Modified:	04 Aug 2023 04:21
URI:	http://repository.its.ac.id/id/eprint/100248

Actions (login required)

View Item