Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Pillar of Physics: Jurnal Berkala Ilmiah Fisika
Mustika, Dian Putri
Unknown Affiliation
Earth & Planetary Sciences Materials Science & Nanotechnology Physics

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
The use of Electronic Nose in Machine Learning-Based of Jengkol (Archidendron Pauchiflorum) Andkabauseeds (Archidendron Bubalinum) Authentication Mustika, Dian Putri; Darvina, Yenni; Yulkifli, Y; Triyana, Kuwat
PILLAR OF PHYSICS Vol 18, No 1 (2025)
Publisher : Department of Physics – Universitas Negeri Padang UNP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/16783171074

Abstract

This research is based on the fact that this difference in economic value can create a potential motive for counterffeiting, although to date there has been no concrete evidence that counterfeiting between these two types of seeds has occurred. Basically, however, jengkol and kabau are also quite similar physically, especially when they are chopped, making it difficult to distinguish them visually even though they have different odors. The sample preparation tools used are digital scales and knives. While the data collection tools used are electronic nose, personal computer, data logger, usb, drain pump, teflon hose, 100 ml beaker, and acrylic box. The materials used are jengkol and kabau seeds.The method used is experimental, where jengkol and kabau are put into a glass beaker which will be tested using an enose connected using a teflon hose and the output results are seen in the data logger.The model used is support vector machine. The performance of the external test data on the SVM model with RBF kernel can be seen in Figure 9. It can be seen that out of 200 data, there are 2 data that are misclassified. Where from the confution matrices, the accuracy is 99.00, Recall_0 is 99.00, and Recall_1 is 99.00. This shows that the model that has been developed remains stable despite changes in the retrieval method and by being carried out in different weeks.
Co-Authors Kuwat Triyana Yenni Darvina Yulkifli, Y