Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Andre Ananda 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 
Implementasi Sistem Pendeteksi Uang pada Celengan Pintar menggunakan Metode Jaringan Syaraf Tiruan Andre Ananda Pratama; Rizal Maulana; Rakhmadhany Primananda
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 5 (2021): Mei 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

The waste of wealth that is owned by the desire to spend it on needs which causes the behavior of a consumptive lifestyle. (C. Lyons, 2004) argues that early education on money management and savings is beneficial for people who will form intelligence and intellectual characteristics in money management as an adult. Therefore, an effective way to avoid this behavior is to save money so that children can achieve financial success in the future. The existence of this problem encourages the author to realize a solution so that it can encourage children to save by making IoT (Internet of Things) -based piggy banks. This smart piggy bank can detect both types of money (metal and paper) by utilizing the TCS3200 sensor as an RGB color detector for money and a loadcell sensor as a sensor to weigh the weight of money. The infrared sensor is also used to detect objects entering from the piggy bank hole. The features used for this implementation will be classified using an Artificial Neural Network (ANN) classification algorithm. MQTT protocol is used to implement an IoT-based system to display the result of the classification from the system to an android application. The training data that used in the study were 96 data. The TCS3200 sensor tested has an accuracy rate of 93.93% and the loadcell HX71 sensor tested has an accuracy rate of 99.61%. Also, testing with the ANN method which was tested on 24 test data showed an accuracy rate of 91.7%. Meanwhile, the time test in determining the nominal class of 10 tests obtained an average value of 13,48 milliseconds.
Co-Authors Rakhmadhany Primananda Rizal Maulana