Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Mohammad Faizal Ajizi
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 Kematangan Buah Pisang Berbasis Sensor Warna Dan Sensor Load Cell Menggunakan Metode Naive Bayes Mohammad Faizal Ajizi; Dahnial Syauqy; Mochammad Hannats Hanafi Ichsan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (534.058 KB)

Abstract

Banana fruit is one of the fruits that are consumed by many people, because bananas contain good nutrition. For this reason, many bananas are cultivated by the community. Banana cultivation is done by banana farmers or ordinary people. To find out the maturity of bananas, generally when still in the tree by looking at the color of the banana peel and by massaging the texture of the banana. But this method has a different level of maturity because everyone's perception is different. For production needs, bananas are needed with the right maturity, for that research is made about the maturity of bananas based on the fruit skin color and the weight of bananas that make decisions using the Naive Bayes method. This prototype was built using a Color Sensor to detect colors from banana peels, and loadcell sensors and HX711 modules to detect the weight of bananas and Arduino Mega as data processors from sensors and to display classification results. Based on the results of system testing, testing for loadcell sensors has an accuracy rate of 93.89% when compared to digital scales. The color sensor gets an accuracy rate of 85.53% compared to Corel Photo-Paint. Of the 10 test data tested, there is 1 data generated by the system that is not in accordance with the actual conditions, then the classification produced by the system has an accuracy rate of 90%.
Co-Authors Dahnial Syauqy Mochammad Hannats Hanafi Ichsan