<![CDATA[COVID-19 has spread all throughout the world, even to Indonesia. Surabaya becomes one of Indonesia's major cities where COVID-19 is fast spreading, culminating in a large number of positive cases and over 1000 deaths from the disease by November 2020. The number of positive COVID-19 cases predicted can be utilized to limit hospital facility availability and develop plans and policies for tackling the illness outbreak. One of the many prediction systems identified is the Extreme Learning Machine (ELM). ELM has a quick and precise training speed. However, the performance of ELM depends on the number of neurons. When the number of neurons is not precisely specified, prediction accuracy suffers. Particle Swarm Optimization (PSO) has the ability to optimize the number of node ELM neurons so the ELM can achieve better results. The number of neurons is determined using Particle Swarm Optimization (PSO) with decreased inertia weight. As a result, this research proposes predicting COVID-19 instances in Surabaya using a hybrid of PSO and ELM (PSO-ELM) with decreased inertia weight. The studies reveal that the offered techniques with different activation functions work comparably well in predicting COVID-19 instances in Surabaya. The best MAPE is achieved using the sigmoid activation function with the number of hidden layer nodes around . Keywords: Covid-19, Optimization, Prediction, PSO-ELM.]]>
Copyrights © 2023
