Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 5 No 8 (2021): Agustus 2021

Klasifikasi Sumber Nektar Madu berdasarkan Kecerahan dan Warna dengan Metode Naive Bayes berbasis Embedded System

Syarief Taufik Hidayatullah (Fakultas Ilmu Komputer, Universitas Brawijaya)
Dahnial Syauqy (Fakultas Ilmu Komputer, Universitas Brawijaya)
Hurriyatul Fitriyah (Fakultas Ilmu Komputer, Universitas Brawijaya)



Article Info

Publish Date
13 Aug 2021

Abstract

Honey is a liquid has many benefits for humans and also as a food reserve for bees, honey stored by bees undergoing chemical processes and fermentation through evaporation, air exchange and changes in increasing heat temperatures. The bees job is divided into three kind, female bees lay eggs, male bees to mate with female bees and the worker bees looking for nectar which is stored in the bee hive as food reserves. Honey from different nectars produces different colors and tastes, so it have different benefits. Honey can be used as a sugar substitute and has many contain beneficial. This design system with naive bayes classification uses acacia honey, eucalyptus honey, coffee honey longan honey, Sengon multiflora honey and mango honey with Arduino Uno microcontroller, TCS3200 sensor and LDR sensor. The classification process is carried out by pouring honey into a 50ml beaker glass then placing it above the LDR sensor and under the TCS3200 sensor according to the prototype design of the calcification tool. The LDR sensor gets light from the color sensor and then will give output red, green, blue, and honey clarity then the data is processed by the naive bayes method so the result will be a classification of honey. Classifications are displayed on the LCD so that users can see the classification results. Naive Bayes classification was chosen because it is effective and requires a bit of training data, in this study using 10 samples of training data per honey. From the test results with 67 honey samples, the results obtained 94% accuracy with an average computation time of 1007.28ms, an average LCD accuracy 100%, an average LDR sensor accuracy 98.9% and an average error on the color sensor 5.69%. This means that the results can be said it's good

Copyrights © 2021






Journal Info

Abbrev

j-ptiik

Publisher

Subject

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Description

Jurnal Pengembangan Teknlogi Informasi dan Ilmu Komputer (J-PTIIK) Universitas Brawijaya merupakan jurnal keilmuan dibidang komputer yang memuat tulisan ilmiah hasil dari penelitian mahasiswa-mahasiswa Fakultas Ilmu Komputer Universitas Brawijaya. Jurnal ini diharapkan dapat mengembangkan penelitian ...