Open AccessPandemic dynamics prediction in Java using the Moving Average method and the Knowledge Growing System (KGS)
Author(s) -
Arwin Datumaya Wahyudi Sumari,
Dimas Rossiawan Hendra Putra,
Muhammad Bisri Musthofa,
Nicola Mari
Publication year - 2020
Publication title -
jurnal teknologi dan sistem komputer
Language(s) - English
Resource type - Journals
eISSN - 2620-4002
pISSN - 2338-0403
DOI - 10.14710/jtsiskom.2020.13779
Subject(s) - java , pandemic , mean absolute percentage error , java programming language , dynamics (music) , time series , statistics , covid-19 , computer science , geography , mean squared error , mathematics , operating system , medicine , physics , disease , pathology , acoustics , infectious disease (medical specialty)
This study aims to analyze the comparative performance of pandemic dynamics prediction methods on the island of Java, based on data from March to May 2020 covering the provinces of DKI Jakarta, West Java, Central Java, DI Yogyakarta, and East Java. The prediction uses Knowledge Growing System (KGS) and time series models, namely Single Moving Average (SMA) and Exponential Moving Average (EMA). Based on the Mean Absolute Percentage Error (MAPE) computational results, the EMA method produces a lower error rate than the SMA method with 47.94 % on average. The KGS prediction with a Degree of Certainty (DoC) produced a trend analysis that the pandemic dynamics in DKI Jakarta province will decrease gradually if the current policy is still implemented. Whereas in the other provinces, the KGS predicted the pandemic dynamics trends will still increase.