Implementation of a genetic algorithm method for stochastic model of COVID-19 in Indonesia

COVID-19 is an infectious disease that has spread to countries in the world, including Indonesia. A stochastic SIR model was constructed to represent the spreading of COVID-19. One of the popular methods in a heuristic search and optimization algorithm, a genetic algorithm method, is implemented to estimate the parameters of the SIR stochastic model. As a result, using the parameters obtained, the stochastic SIR model can be in line with the actual data, and we get accurate predictions within four weeks later. © 2022 Author(s).

COVID-19 Outbreak Prediction in Indonesia Based on Machine Learning and SIRD-BasedHybrid Methods

This paper aims to forecast and analyze the spread of COVID-19 outbreak in Indonesia by applying machine learning and hybrid approaches. We show the performance of each method, an ensemble-support vector regression (ensemble-SVR), a genetic algorithm and an SIRD model (GA-SIRD) and an extended Kalman filter, a genetic algorithm and an extended Kalman filter (EKF-GA-SIRD), in obtaining the prediction of the outbreak. The GA-SIRD model is built based on the data availability and is enhanced by employing an extended Kalman filter to better predict the spread of the outbreak. Without considering the epidemic model, the ensemble SVR can provide a higher accuracy compare to the two hybrid approaches in the case of short-term forecasting. Furthermore, the EKF-GA-SIRD can better adapt to the extreme change and shows a better performance than the GA-SIRD. © 2021.

Epidemic modeling of COVID-19 in the ASEAN countries using a genetic partial fitting algorithm with the presence of a second wave

We present an SIRD epidemic modelling for COVID-19 outbreak in the ASEAN member countries. The occurrence of a second wave in the region adds complexity to the parameter estimation of the SIRD model. In this case, a standard genetic algorithm cannot fully capture the dynamic transmission of the pandemic. We therefore introduce a genetic partial fitting algorithm (GPFA) of seven-day intervals. We show that our method outperforms the standard algorithm with a significant reduction in the Root Mean Square Error (RMSE) value. We also extend our study to produce a real-time estimation of the effective reproduction number with a confidence interval to incorporate uncertainties in the model. © The Author(’s).

How Many Can You Infect? Simple (And Naive) Methods Of Estimating The Reproduction Number

This is a pedagogical paper on estimating the number of people that can be infected by one infectious person during an epidemic outbreak, known as the reproduction number. Knowing the number is crucial for developing policy responses. There are generally two types of such a number, i.e., basic and effective (or instantaneous). While basic reproduction number is the average expected number of cases directly generated by one case in a population where all individuals are susceptible, effective reproduction number is the number of cases generated in the current state of a population. In this paper, we exploit the deterministic susceptibleinfected-removed (SIR) model to estimate them through three different numerical approximations. We apply the methods to the pandemic COVID-19 in Italy to provide insights into the spread of the disease in the country. We see that the effect of the national lockdown in slowing down the disease exponential growth appearedabout two weeks after the implementation date. We also discuss available improvements to the simple (and naive) methods that have been made by researchers in the field. Authors of this paper are members of the SimCOVID-(Simulasi dan Pemodelan COVID-19 Indonesia) collaboration.

Data-driven modeling and forecasting of COVID-19 outbreak for public policy making.

This paper presents a data-driven approach for COVID-19 modeling and forecasting, which can be used by public policy and decision makers to control the outbreak through Non-Pharmaceutical Interventions (NPI). First, we apply an extended Kalman filter (EKF) to a discrete-time stochastic augmented compartmental model to estimate the time-varying effective reproduction number (Rt). We use daily confirmed cases, active cases, recovered cases, deceased cases, Case-Fatality-Rate (CFR), and infectious time as inputs for the model. Furthermore, we define a Transmission Index (TI) as a ratio between the instantaneous and the maximum value of the effective reproduction number. The value of TI indicates the "effectiveness" of the disease transmission from a contact between a susceptible and an infectious individual in the presence of current measures, such as physical distancing and lock-down, relative to a normal condition. Based on the value of TI, we forecast different scenarios to see the effect of relaxing and tightening public measures. Case studies in three countries are provided to show the practicability of our approach.