Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Andhika Nino Pratama
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Klasifikasi Kandungan Boraks pada Gendar menggunakan Sensor Warna dengan Metode Jaringan Syaraf Tiruan berbabsis Arduino Andhika Nino Pratama; Dahnial Syauqy; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 6 (2022): Juni 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Gendar is one of the traditional foods typical of Central Java that can be found until now. The texture of the gendar itself is like rice cake or ketupat but is more chewy and has a more savory taste. In ancient times, the use of bleng salt or what is now called borax was commonly used in the process of making gendar because it can provide a savory taste of food and provide a legit and chewy texture as well as a preservative for gendar. Borax is a dangerous chemical compound which if consumed by the body does not cause an immediate reaction. The safe limit for the use of borax itself is 1 gram in 1 kg of food and the fatal dose when consumed and enters the body for children is 3 - 6gr and for adults is 15 - 20gr. The rampant ignorance of the public regarding the safe limits of borax that enters the body has prompted researchers to design a system that can classify the borax content in gendar based on 3 classes, namely no borax, light borax, and heavy borax. The system utilizes Arduino Uno as a data processor and classification calculation, a color sensor that is used as a color detector for the gendar object being tested, and a 16x2 LCD to display the classification results. The classification process itself uses the backpropagation artificial neural network classification method. Based on the system testing process, of the 30 samples tested, 90% accuracy was obtained with the average computation time required by the backpropagation Neural Network in the classification process is 3057ms or 3 seconds and 0.057 seconds.
Co-Authors Dahnial Syauqy Edita Rosana Widasari