DISKRIMINASI CITRA DAGING BABI DAN SAPI MENGGUNAKAN THIRD GENERATION OF UIN SUNAN KALIJAGA’S HIGH POWER UV-LED FLUORESCENCE SPECTRO-IMAGING SYSTEM TERKOMBINASI DEEP LEARNING BERALGORITMA CNN

Rai Husnul Arifah, NIM.: 18106020006 (2022) DISKRIMINASI CITRA DAGING BABI DAN SAPI MENGGUNAKAN THIRD GENERATION OF UIN SUNAN KALIJAGA’S HIGH POWER UV-LED FLUORESCENCE SPECTRO-IMAGING SYSTEM TERKOMBINASI DEEP LEARNING BERALGORITMA CNN. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (DISKRIMINASI CITRA DAGING BABI DAN SAPI MENGGUNAKAN THIRD GENERATION OF UIN SUNAN KALIJAGA’S HIGH POWER UV-LED FLUORESCENCE SPECTRO-IMAGING SYSTEM TERKOMBINASI DEEP LEARNING BERALGORITMA CNN) 18106020006_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (3MB) | Preview
	Text (DISKRIMINASI CITRA DAGING BABI DAN SAPI MENGGUNAKAN THIRD GENERATION OF UIN SUNAN KALIJAGA’S HIGH POWER UV-LED FLUORESCENCE SPECTRO-IMAGING SYSTEM TERKOMBINASI DEEP LEARNING BERALGORITMA CNN) 18106020006_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (5MB) | Request a copy

Abstract

This research was motivated by the rampant counterfeiting of beef with pork. This is contraried to the Islamic teachings regarding the prohibition of consuming pork. Real-time PCR has been used to discriminate against pork and beef. However, sample preparation was complicated and equipment investment was expensive, so it is necessary to develop alternative discrimination methods. This study aimed to acquire pork and beef fluorescence images using the third generation of UIN Sunan Kalijaga's high power UV-LED fluorescence spectro-imaging system and to discriminate them using deep learning with the CNN algorithm. This research was conducted in two stages, namely data collecting and processing. The data collection stage was carried out by acquiring every 60 pieces of pork and 60 pieces of beef samples using the third generation of UIN Sunan Kalijaga's high power UV-LED fluorescence spectro-imaging system to obtain 220 fluorescence images of pork and beef. Data processing consists of tools and materials preparation, preprocessing, making deep learning, training and validation, and testing. Training and validation of deep learning were carried out using each 100 fluorescence image data from pork and beef, namely 80 training data and 20 validation data. Meanwhile, the testing used 10 fluorescence image test data from pork and 10 fluorescence image test data from beef. The results showed that fluorescence images from pork and beef were successfully acquired using the third generation of UIN Sunan Kalijaga's high power UV-LED fluorescence spectro-imaging system and well discriminated by deep learning with CNN algorithm with an accuracy of 100%.

Share this knowledge with your friends :

Actions (login required)

View Item