Article Per Year (5 Year)
p-Index From 2020 - 2025
4.589
P-Index
This Author published in this journals
All Journal Dinamik Agrikultura Jurnal Informatika dan Teknik Elektro Terapan Infotech Journal Jurnal Pilar Nusa Mandiri JOURNAL OF APPLIED INFORMATICS AND COMPUTING J-SAKTI (Jurnal Sains Komputer dan Informatika) JOURNAL INFORMATICS, SCIENCE & TECHNOLOGY JATI (Jurnal Mahasiswa Teknik Informatika) J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Teknologi Sistem Informasi Jurnal Pustaka Data : Pusat Akses Kajian Database, Analisa Teknologi, dan Arsitektur Komputer Jurnal Informatika dan Rekayasa Komputer
Umaidah, Yuyun
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Industrial & Manufacturing Engineering Mechanical Engineering

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Informatika dan Rekayasa Komputer

 1 
Prediksi Curah Hujan Menggunakan Jaringan Syaraf Tiruan Backpropagation pada Software Matlab Prasetya, Muhammad Erlangga; Ryansyah, Eddy; Rusfauzi Surya, Muhammad; Umaidah, Yuyun
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 5 No 2 (2025): JAKAKOM Vol 5 No 2 SEPTEMBER 2025
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2025.5.2.2398

Abstract

This study aims to design and implement a rainfall prediction model using the Artificial Neural Network (ANN) approach with the backpropagation learning algorithm on the Matlab platform. Rainfall prediction is an important aspect in agriculture, hydrology, and water resources management, which requires accurate and adaptive methods to seasonal data patterns. In this study, monthly rainfall data for Bogor City for the period 2020-2022 was used as the training and testing dataset. The data was normalized using the sigmoid activation function to improve the network training performance. The network architecture consists of 12 input neurons, 10 hidden neurons, and 1 output neuron. The training results showed an error rate (Mean Squared Error) of 0.00090677 with a regression value of 0.99022, while the test results produced a regression of 0.98837. These findings indicate that the backpropagation method in ANN is able to predict rainfall effectively and accurately. This model can be further developed to predict other weather phenomena.
Co-Authors Agustin, Amellia Veronica Alexander, Hizkia Anesha Lutia, Frise Apriade Voutama Arga Adi Putra, Harvian Aries Suharso Aufarrizqi, Adrian Carudin, Carudin Destiana, Tiara Eddy Ryansyah Enri, Ultach Fadhilah, Muhammad Rizqi Fadlurrahman Muchdyansyah, Raihan Farissa, Riva Arsyad Fauzan, Muh. Yoga Fitrianti, Ika garno, Garno Hakim, Reza Hannie, Hannie Haya Amalia, Salma Hidayatullah, Haikal Iqbal Maulana Jajuli, M. Jamaludin, Asep Maemunah Maharadja, Alfanda Novebrian Mahatmayana, I Ketut Manu Mayasari, Rini Meila Azzahra Sofyan, Fazrin Muhaa, Najibah Aisyah Mulyono, Larasati Mya Nur Amalia, Indira Nursidik Dinar, Ahmad Nursyahfitri, Rika Padilah, Tesa Nur Pajri, Dicki Permana, Hendi Pramudja, Stevanus Ertito Prasetya, Muhammad Erlangga Pratama, Aditiya Yoga Pratama, Sena Purwantoro Putri Riyandoro, Affani Rusfauzi Surya, Muhammad Sa'adah, Fitria Nur Safitri, Tiara Suhaeni Suhaeni, Suhaeni Susilo Yuda Irawan, Agung Suyantoputri, Fanny Trihandoko, Kardo Vito Anggoro, Alfian