Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Zanna Annisa Nur Azizah Fareza
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search
Journal : Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer

 1 
Prediksi Hasil Panen Tanaman Biofarmaka di Indonesia dengan Menggunakan Metode Extreme Learning Machine Zanna Annisa Nur Azizah Fareza; Imam Cholissodin; Lailil Muflikhah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 11 (2022): November 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Biopharmaceutical plants are a type of horticultural plants that are used as ingredients for medicines, herbs, cooking spices and cosmetic ingredients. Biopharmaceutical plants are used as alternative medicines for various diseases and are believed to increase the body's immunity by processing them into herbs and medicines. Biopharmaceutical plants as raw materials for medicines make a major contribution to Indonesia's export activities and are in high demand due to the development of the traditional medicine industry, but the yields of biopharmaceutical plants are very unstable. Therefore, to be able to estimate the yield of biopharmaceutical crops, a prediction must be made using the Extreme Learning Machine (ELM) method. The stages of making predictions with this method start from the pre-processing process, data normalization, training process, testing process, denormalization, and evaluating error values using MAPE. This method has advantages related to fast computation compared to other neural network methods. In this study, data ratio parameters were tested with holdout validation based on nested cross validation, features, and hidden neurons. From the results of the tests that have been carried out, the optimal parameter is obtained with the smallest MAPE value of 9.34%.
Co-Authors Imam Cholissodin Lailil Muflikhah