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
Putri Indhira Utami Paudi
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

 1 
Implementasi Metode Extreme Learning Machine (ELM) untuk Memprediksi Jumlah Debit Air yang Layak Didistribusi (Studi Kasus: PDAM Kabupaten Gowa Makassar) Putri Indhira Utami Paudi; Muhammad Tanzil Furqon; Sutrisno Sutrisno
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 3 (2020): Maret 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (392.707 KB)

Abstract

PDAM Gowa Regency, Makassar City is a company under the government that carries out the process of water production and continues to distribute the PDAM water to home residents. If there is a lot if water produced, it means theres is also a large amount of water that available for PDAM, so it can fulfill the public's requirement and can even to add customers. However, the seasonal change factor can take effect the discharge of water produced. So, the main problem is the uncertainty of water production which will certainly have an impact of the PDAM water distribution that will be distributed to home residents. But not all the water produced can be distributed because it has to go through several stages of water quality checking, so that the water that's distributed is in accordance with the standarts set by the government. Therefore, preduction of a proper flow of water distributed by PDAM is needed, with the aim that PDAM can adjust the proper flow of water distributed to customers. This research applies Extreme Learning Machine (ELM) method to forecast using single variable dan multivariate data types. The process of applying the ELM methods are normalizing, process of training and testing, denormalizing, and evaluating the prediction results using Mean Percentage Absolute Error (MAPE). Depend on the application of the ELM method and the testing process, it produces the best conditions of single data variable when using 7 input neurons, 4 hidden neurons, 20 training data and 5 testing data to produced an average MAPE of 3.938%, while using the multivariate data, the average MAPE was 13.081% using 4 hidden neurons, 30 training data and 5 testing data.
Co-Authors Muhammad Tanzil Furqon Sutrisno Sutrisno