Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining
Sagita Sasmita Wijaya
Universitas Multimedia Nusantara
Computer Science & IT

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

Found 1 Documents
Search

 1 
Small Timescaled Data for Covid-19 Prediction with RNN-LSTM in Tangerang Regency Sagita Sasmita Wijaya; Marlinda Vasty Overbeek
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.21676

Abstract

Throughout the pandemic, many people have become familiarised with the new type of virus that has been spreading throughout the world, called the Coronavirus. On the 2nd of March, the year 2020, the Indonesian government had announced the identification of first Covid-19 case in Indonesia. With the arrival of Covid-19, and its spreading across all the provinces of Indonesia, the number of positive cases keeps growing even in the present day. Tangerang Regency is one of the areas that has opaqued citizens in the Banten Province. The purpose of this research is to discuss how to predict the sum of Covid-19 cases in the Tangerang Regency using the RNN-LSTM method. Although this method is very eloquent if used to perform a sequential task, its complexity and loss of gradient can make this model difficult to be trained, hence resulting in the use of the Long Short-Term Memory (LSTM) to reduce these weaknesses and help the RNN to look back on past data. This research uses Python as the programming language and Jupyter Notebook for the visualization of the results of the prediction. Therefore, the prediction model has been evaluated using various computational methods, such as RMSE with its error percentage of 0.05, and MSE and MAE with the same error percentage of 0.03 with the loss of their models being 9.6793e-04.
Co-Authors Marlinda Vasty Overbeek