istiadi, ardhi and Sulistiyanti, Sri Ratna and herlinawati, herlinawati and Fitriawan, Helmy (2019) Model Design of Tomato Sorting Machine Based on Artificial Neural Network Method Using Node MCU Version 1.0. In: ICETSAS 2018, 18 Oktober 2018, Hotel Emersia Bandar Lampung.

[img] Text
Istiadi_2019_J._Phys.__Conf._Ser._1376_012026.pdf

Download (558kB)
Official URL: https://iopscience.iop.org/issue/1742-6596/1376/1

Abstract

Tomatoes have different quality and maturity, this is a problem in sorting because it is often wrong on put the grade of tomato marketing and takes a long time in sorting. One solution offered to overcome this problem is a tomato sorting system based on artificial neural network method that can minimizes the sorting time and also places the tomato according to grade. In this research, the model of artificial neural network system backpropagation method on microcontroller NodeMCU Lua version 1.0. The artificial neural network method is used to process the image of tomato objects moving through conveyor in the form of RGB value and captured by color sensor TCS 3200, the image obtained can classify the grade of tomatoes into unripe, half ripe and ripe. This research compared the results of training and testing of artificial neural networks between Matlab R2015a and NodeMCU Lua version 1.0. The outputs or decisions of artificial neural networks will be forwarded to the control system in the form of hardware and software used in this research. The results showed that the tomato sorting model successfully classified the tomato grade, and was able to control motor servo & DC motor automatically based on RGB value with processing time about 5 seconds and error 8.3%.

Item Type: Conference or Workshop Item (Paper)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Teknik (FT) > Prodi Teknik Elektro
Depositing User: Dr. Sri Ratna Sulistiyanti
Date Deposited: 14 Nov 2019 11:04
Last Modified: 14 Nov 2019 11:04
URI: http://repository.lppm.unila.ac.id/id/eprint/16189

Actions (login required)

View Item View Item