Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan
The artificial neural network (ANN) technology in rainfall prediction can be done using the learning approach. The ANN prediction accuracy is measured by the determination coefficient (R2) and root mean square error (RMSE). This research implements Elman’s Recurrent ANN which is heuristically optimi...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Bina Nusantara University
2011-06-01
|
Series: | ComTech |
Subjects: | |
Online Access: | https://journal.binus.ac.id/index.php/comtech/article/view/2707 |
id |
doaj-09d44aae42fe47a291bf2aa7ff2b28b8 |
---|---|
record_format |
Article |
spelling |
doaj-09d44aae42fe47a291bf2aa7ff2b28b82020-11-25T02:48:05ZengBina Nusantara UniversityComTech2087-12442476-907X2011-06-0121233510.21512/comtech.v2i1.27072107Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah HujanAfan Galih Salman0Yen Lina Prasetio1Bina Nusantara UniversityBina Nusantara UniversityThe artificial neural network (ANN) technology in rainfall prediction can be done using the learning approach. The ANN prediction accuracy is measured by the determination coefficient (R2) and root mean square error (RMSE). This research implements Elman’s Recurrent ANN which is heuristically optimized based on el-nino southern oscilation (ENSO) variables: wind, southern oscillation index (SOI), sea surface temperatur (SST) dan outgoing long wave radiation (OLR) to forecast regional monthly rainfall in Bongan Bali. The heuristic learning optimization done is basically a performance development of standard gradient descent learning algorithm into training algorithms: gradient descent momentum and adaptive learning rate. The patterns of input data affect the performance of Recurrent Elman neural network in estimation process. The first data group that is 75% training data and 25% testing data produce the maximum R2 leap 74,6% while the second data group that is 50% training data and 50% testing data produce the maximum R2 leap 49,8%.https://journal.binus.ac.id/index.php/comtech/article/view/2707artificial neural network, coefficient deteminationi (R2), root mean square error (RMSE), gradient descent adaptive learning rate and momentum, ENSO |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Afan Galih Salman Yen Lina Prasetio |
spellingShingle |
Afan Galih Salman Yen Lina Prasetio Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan ComTech artificial neural network, coefficient deteminationi (R2), root mean square error (RMSE), gradient descent adaptive learning rate and momentum, ENSO |
author_facet |
Afan Galih Salman Yen Lina Prasetio |
author_sort |
Afan Galih Salman |
title |
Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan |
title_short |
Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan |
title_full |
Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan |
title_fullStr |
Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan |
title_full_unstemmed |
Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan |
title_sort |
implementasi jaringan syaraf tiruan recurrent menggunakan gradient descent adaptive learning rate and momentum untuk pendugaan curah hujan |
publisher |
Bina Nusantara University |
series |
ComTech |
issn |
2087-1244 2476-907X |
publishDate |
2011-06-01 |
description |
The artificial neural network (ANN) technology in rainfall prediction can be done using the learning approach. The ANN prediction accuracy is measured by the determination coefficient (R2) and root mean square error (RMSE). This research implements Elman’s Recurrent ANN which is heuristically optimized based on el-nino southern oscilation (ENSO) variables: wind, southern oscillation index (SOI), sea surface temperatur (SST) dan outgoing long wave radiation (OLR) to forecast regional monthly rainfall in Bongan Bali. The heuristic learning optimization done is basically a performance development of standard gradient descent learning algorithm into training algorithms: gradient descent momentum and adaptive learning rate. The patterns of input data affect the performance of Recurrent Elman neural network in estimation process. The first data group that is 75% training data and 25% testing data produce the maximum R2 leap 74,6% while the second data group that is 50% training data and 50% testing data produce the maximum R2 leap 49,8%. |
topic |
artificial neural network, coefficient deteminationi (R2), root mean square error (RMSE), gradient descent adaptive learning rate and momentum, ENSO |
url |
https://journal.binus.ac.id/index.php/comtech/article/view/2707 |
work_keys_str_mv |
AT afangalihsalman implementasijaringansyaraftiruanrecurrentmenggunakangradientdescentadaptivelearningrateandmomentumuntukpendugaancurahhujan AT yenlinaprasetio implementasijaringansyaraftiruanrecurrentmenggunakangradientdescentadaptivelearningrateandmomentumuntukpendugaancurahhujan |
_version_ |
1724750144307462144 |