Jurnal Teknoinfo
Vol 17, No 2 (2023): Vol 17, No 2 (2023) : JULI

DESAIN MODEL IDENTIFIKASI DINI PEMANFAATAN TANAMAN AROMATIK INDONESIA

Adriana Sari Aryani ((Sinta ID : 6646184) Ilmu Komputer, Universitas Pakuan)
Hermawan Taher (Universitas Pakuan Bogor)
Kotim Subandi (Universitas Pakuan Bogor)



Article Info

Publish Date
12 Jul 2023

Abstract

The fragrance industry is estimated to grow 3.9% per year until 2025 with a tendency to move from synthetic raw materials to natural sources. Fragrance ingredients are used for perfume, flavor, aromatherapy, or various other purposes. Indonesia has a variety of aromatic plants which are raw materials for fragrances, but not all of them have been identified properly. Early identification of the use of aromatic plants in Indonesia can be done by conducting organoleptic observations on plant specimens. Input data can be in the form of symphysia or extracts from plants whose sources have been identified. The identification method was developed using the Fault Tree Analysis model, in which the failure mode is used to filter out the possibility of tracking the plant so that it does not enter the next selection event. There are three top events to be achieved, namely the use of aromatic plants as perfume, flavors, and aromatherapy. Data that cannot reach one of the top events are categorized as unidentified aromatic plants or non-aromatic plants. The test results using 100 Indonesian plants data that were suspected to be aromatic, concluded that 25 plants were for perfume, 63 were for flavor, 24 were for aromatherapy, 6 were indicated for aromatic but their use had not been confirmed, and 11 were non-aromatic plants. The early identification model for the use of aromatic plants using the Fault Tree Analysis approach after being validated with the Cofussion Matrix method, has an average precision of 84.35% with an accuracy of 86.23%. Identification of aromatic plants for flavoring ingredients has a precision of 98.36% with an accuracy of 97.27%, although it is also good for predicting the use of fragrances and aromatherapy.

Copyrights © 2023






Journal Info

Abbrev

teknoinfo

Publisher

Subject

Computer Science & IT

Description

Jurnal Teknoinfo is a peer-reviewed scientific Open Access journal that published by Universitas Teknokrat Indonesia. This Journal is built with the aim to expand and create innovation concepts, theories, paradigms, perspectives and methodologies in the sciences of Informatics Engineering. The ...