Characteristic Parameters of Epoch Deep Learning to Predict Covid-19 Data in Indonesia
Widi Hastomo, Adhitio Satyo Bayangkari Karno, Nawang Kalbuana, Andri Meiriki, Sutarno Sutarno
Abstract
Abstract This study aims to predict Covid-19 data in Indonesia using LSTM machines learning and GRU using python. As a comparison, two datasets from other countries which have strong correlation were used. The dataset is of the ourworldindata.org page. The results of the LSTM model with epoch 15, RMSE 68,417 require rapid processing time and better accuracy than GRU with epoch 400, RMSE 90,173. The results from Covid-19 data processing in Indonesia have a robust correlation with Covid-19 data in Azerbaijan, Bangladesh, Bhutan, Cape Verde, Curacao, Slovenia, South Africa, and Thailand. The epoch characteristics of LSTM and GRU are a challenge since the amount of Covid-19 data is relatively minor.