No abstract

No abstract

This study aims to examine the architectural performance of the Recurrent Neural Network (RNN) model in predicting Covid-19 cases in Lampung Province. The RNN method is part of Deep Learning which will be used to model data on Covid-19 cases in Lampung Province from March 26, 2020 to March 28, 2021. The RNN model was chosen because the Covid-19 data is in the form of a time series and the advantages of RNN are that it can capture information on the data time series using multiple network layers which allow better modeling and resulting in high prediction accuracy. The data is divided into 3, namely active cases, recovered cases, and dead cases. After preparing the data, the 368 data were divided into 294 initial latih data and 74 test data. After latih on the data for each data, then a test is carried out on the data for each data as a reference for predicting the latest data. The most optimal results show the cumulative active case model with RMSE=0.0022; for cumulative recovery cases obtained RMSE = 0.0007; while the cumulative death cases obtained RMSE = 0.0012. Based on the modeling error, then make predictions on the three cases which results in RMSE = 0.001 for cumulative active cases; RMSE=0.0027 for cumulative recovery cases; and RMSE=0.001 for cumulative death cases.

In this paper, the generation of surface waves by wind is modeled using an extended shallow water model. Jeffreys’ sheltering mechanism is incorporated to model the wind action on the surface. This modification allows the model to have a wave grow or decay mechanism under the action of wind. The wave generation or damping is investigated by calculating critical wind velocity to excite oscillatory waves on the surface. The result shows that critical wind is proportional to a numerical constant, namely the sheltering coefficient, which related to the capability of wave overcome the wind gust. Thus this model has the convenience that the critical wind speed may comparable to physical data for a suitable choice of this constant.

No abstract