A novelty classification model for varied agarwood oil quality using the K-Nearest Neighbor algorithm / Aqib Fawwaz Mohd Amidon … [et al.]
Agarwood oil, in general, has become a highly advertised and in great demand commodity on the global market. The use of agarwood oil in the manufacturing of fragrances, medicine, and religious rites and festivities makes it even more important. Agarwood oil, on the other hand, never has a systematic...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Book Section |
Language: | English |
Published: |
Faculty of Computer and Mathematical Sciences
2022
|
Subjects: | |
Online Access: | https://ir.uitm.edu.my/id/eprint/69561/1/69561.pdf https://ir.uitm.edu.my/id/eprint/69561/ https://jamcsiix.wixsite.com/2022 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Agarwood oil, in general, has become a highly advertised and in great demand commodity on the global market. The use of agarwood oil in the manufacturing of fragrances, medicine, and religious rites and festivities makes it even more important. Agarwood oil, on the other hand, never has a systematic grading system. As a result, each producing country must develop its own method for distinguishing between high-quality and low-quality agarwood oil. According to previous research, the current classification method relies solely on expert people in the search for agarwood in the forest. Their services are used to sniff and evaluate each agarwood to determine if it is of high quality or not. Unfortunately, this method has many shortcomings. Among other things, it will cause the health of those involved to be affected, require a long period of time to assess one by one, and certainly contribute to high operating costs. As a result, a new grading system based on artificial algorithms, namely K-Nearest Neighbor algorithms, was established. The value of the percentage of the quantity of significant chemical components contained in the agarwood oil samples is used to classify the agarwood oil samples using this method. Therefore, our algorithm has correctly assessed five distinct agarwood oil grades, according to the performance measure. Certainly, this research can contribute to future research, particularly in the field of data analysis involving agarwood oil grading development. |
---|