Ginanjar, Ariska (2019) SISTEM DETEKSI JENIS CACAT BIJI KOPI DENGAN ALGORITMA K-NEAREST NEIGHBOR. Tugas Akhir thesis, University of Technology Yogyakarta.
|
Text
Naskah Publikasi-Ariska Restu Ginanjar-5150411169.pdf Download (655kB) | Preview |
Abstract
Coffee is one of the leading commodities from Indonesia which produces a kind of beverage. The quality of the drink is determined by the quality of the coffee beans used. One of the quality of coffee beans is based on test defects. Defect test is a test to add up the value of the coffee bean defect value and the amount of defect value based on the type of coffee bean defect. In certain conditions humans can not determine the type of coffee bean defects properly, such as when sick or tired, resulting in inaccuracy in determining the type of defect. Other conditions such as problems with the human senses such as color blindness. The research aims to find a system that can detect types of coffee bean defects with the k-nearest neighbor algorithm the distance formula euclidean, manhattan, and minkowski with RGB and HSV color model features. The results of this study with training data of 60 and test data of 40 found that the best system in the detection system of coffee bean defect types with the k-nearest neighbor algorithm is a k value of 3 and with HSV color model features for all euclidean, manhattan and minkowski formulas get 97% accuracy. Keywords: Coffee, Type of defect, K-Nearest Neighbor
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 27 Oct 2019 23:44 |
| Last Modified: | 27 Oct 2019 23:44 |
| URI: | http://eprints.uty.ac.id/id/eprint/3573 |
Actions (login required)
 |
View Item |
