Penerapan Metode Klasifikasi Adulteran Minyak Babi pada Produk Minyak Menggunakan Sistem Pencitra Berbasis UV dengan Algoritma Support Vector Machine

Sadida, Adzra Amany (2025) Penerapan Metode Klasifikasi Adulteran Minyak Babi pada Produk Minyak Menggunakan Sistem Pencitra Berbasis UV dengan Algoritma Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5009211029-Undergraduate-Thesis.pdf - Accepted Version Restricted to Repository staff only Download (7MB)

Abstract

Minyak babi sering digunakan pada berbagai macam produk makanan lainnya karena memiliki komposisi asam lemak yang serupa dan dapat mengurangi biaya produksi, salah satunya pada produk minyak. Diimplementasikan sistem pencitra berbasis UV untuk klasifikasi adulteran minyak babi pada produk minyak berdasarkan sinyal optik yang dapat merubah profil warna produk minuak. Dilakukan kuantifikasi warna dari produk minyak berdasarkan ruang warna RGB dan HSV dengan momen warna yang terdiri dari mean, standar deviasi, skewness, dan kurtosis. Klasifikasi dilakukan untuk produk minyak murni dan adulteran minyak babi pada produk minyak menggunakan support vector machine (SVM). Didapatkan hasil performansi dengan akurasi 95,83% menggunakan parameter C sebesar 1, gamma sebesar 0,1, dan kernel rbf pada model SVM untuk klasifikasi produk minyak murni dan performansi adulteran minyak babi pada produk minyak nabati 96,52% dan produk minyak hewani 91,66% menggunakan parameter C sebesar 1, gamma sebesar 0,01, dan kernel rbf pada model SVM untuk klasifikasi adulteran.
==========================================================================================================================================
Lard is often used in various other food products because it has a similar fatty acid composition and can reduce production costs, one of which is in oil products. A UV-based imaging system is implemented for the classification of lard adulterants in oil products based on its optical signal that can change the color profile of oil products. Color quantification of oil products based on RGB and HSV color space with color moments consisting of mean, standard
deviation, skewness, and kurtosis. Classification was performed for pure oil products and lard adulterants in oil products using support vector machine (SVM). Performance results were obtained with an accuracy of 95.83% using parameters C of 1, gamma of 0.1, and rbf kernel in the SVM model for the classification of pure oil products and performance of lard adulterants in vegetable oil products 96.52% and animal oil products 91.66% using parameters C of 1, gamma of 0.01, and rbf kernel in the SVM model for adulterant classification.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	fitur warna, klasifikasi, minyak babi, produk minyak sistem pencitra ============================================================ classification, color feature, imaging system, lard, oil products
Subjects:	Q Science > QC Physics > QC475 Photoluminescence T Technology > T Technology (General) T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > TP Chemical technology > TP669 Oils, fats, and waxes
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Adzra Amany Sadida
Date Deposited:	04 Aug 2025 12:00
Last Modified:	04 Aug 2025 12:00
URI:	http://repository.its.ac.id/id/eprint/126839

Actions (login required)

View Item