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
Luqmanul Halim Zain
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 
Sistem Deteksi Kematangan Buah Mangga berdasarkan kandungan Gas NH3, C2H5OH dan VOCs menggunakan metode K-Nearest Neighbor (K-NN) Luqmanul Halim Zain; Eko Setiawan; Hurriyatul Fitriyah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 9 (2021): September 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Mango is a fruit from a tropical climate besides having an interesting taste characteristic, mangoes have various nutritional content and a distinctive aroma. Mango (Mangifera indica L.) has more than 270 aroma of volatile compounds in different mango varieties (Shibamoto, T. et al, 1990). One of the problems in mango production is the classification process for whether mangoes are ripe. In the case of ripe mangoes, sometimes there are mangoes that have a fairly ripe color but still taste sour, and vice versa. Because of that we need a system that can determine the level of maturity of mangoes based on aroma. In this study, a system was designed to detect ripeness in mangoes based on aroma using the K-Nearest Neighbor method. In the process of classifying the sample data, Arduino nano is used as data processing. The training data is taken from mangoes with different ripeness levels, after that the tested mangoes will be detected their gas content with TGS2602, MQ135 and MQ5 sensors, after data has been obtained it will be processed by the K-Nearest Neigbour method. The classification results of the mango ripeness level will be displayed on the LCD screen along with the sensor readings. In system testing, the results classification accuracy with 15 test data, the highest accuracy reached 86.6% at K = 3 compared to the values of K = 5.7 and 9.
Co-Authors Eko Setiawan Fitriyah, Hurriyatul