Journal of Mathematics and Scientific Computing With Applications
Vol. 2 No. 1 (2021)

FORECASTING THE NUMBER OF COVID-19 SUFFERERS IN NORTH SUMATRA USING THE AUTOMATIC CLUSTERING FUZZY TIME SERIES MARKOV CHAIN METHOD

Anggi Ramadany Siregar (Department of Mathematics, Universitas Islam Negeri Sumatera Utara, Medan, Indonesia)
Rina Filia Sari (Department of Mathematics, Universitas Islam Negeri Sumatera Utara, Medan, Indonesia)
Rina Widyasari (Unknown)



Article Info

Publish Date
04 Jan 2021

Abstract

Corona virus is a virus that is currently endemic throughout the world, including in Indonesia, one of which is in North Sumatra Province, because this virus has claimed many victims. North Sumatra Province in positive cases of Covid-19 is ranked 13th out of 34 provinces in Indonesia. The government's anticipation in handling Covid-19 cases is by forecasting the number of positive Covid-19 cases. One of the methods used to forecast Covid-19 sufferers is the Automatic Clustering Fuzzy Time Series Markov Chain method. The Fuzzy Time Series Markov Chain method is used to resolve the deviation value from a forecasted value, while Automatic Clustering is used to determine the length of the interval by grouping numerical data. Then the error calculation will be carried out using the Mean Absolute Percentage Error (MAPE) to determine the level of accuracy of the forecasting model that has been made. The parameter used in this study is the number of Covid-19 sufferers. The results of this study from data on the number of Covid-19 sufferers have a MAPE value of 4.53%. The MAPE value which is less than 10% means that the forecasting of this study has very good criteria. So the Automatic Clustering Fuzzy Time Series Markov Chain method is very good to be applied in forecasting the number of Covid-19 sufferers in North Sumatra Province.

Copyrights © 2021






Journal Info

Abbrev

jmscowa

Publisher

Subject

Mathematics

Description

Journal of Mathematics and Scientific Computing With Applications is a broad-based journal covering all branches of computational or applied mathematics with special encouragement to researchers in theoretical computer science and mathematical computing. It covers all major areas, such as numerical ...