Comparison multi-layer perceptron and linear regression for time series prediction of novel coronavirus covid-19 data in West Java
Open Access
- 1 January 2021
- journal article
- research article
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1722 (1), 012021
- https://doi.org/10.1088/1742-6596/1722/1/012021
Abstract
Until now, the pandemic conditions of Covid-19 are still ravaging the world, even in Indonesia and West Java. Various attempts have been made to stop it. West Java implements Large Scale Social Restrictions, is known as Pembatasan Sosial Skala Besar (PSBB). However, over time, a discourse emerged to loosen PSBB. One of the World Health Organization's (WHO) requirements to loosen is the effective reproduction rate of Corona Virus cases below 1. Therefore, this study focuses on predicting the number of cases in West Java. The methods based on multi-layer perception (MLP) and linear regression (LR). The data were obtained from the C Covid -19 positive case from March to mid-August 2020 in West Java. The experiments show that MLP reaches optimal if it used 13 hidden layers with learning rate and momentum = 0.1. The MLP had a smaller error than LR. Both of them predict the number of cases in the next 30 days from August 14, 2020. The results show that West Java will still have an increase in the number of new cases of Covid -19.This publication has 13 references indexed in Scilit:
- Dysregulation of Immune Response in Patients With Coronavirus 2019 (COVID-19) in Wuhan, ChinaClinical Infectious Diseases, 2020
- Radiological findings from 81 patients with COVID-19 pneumonia in Wuhan, China: a descriptive studyThe Lancet Infectious Diseases, 2020
- Multiple linear regression model of Golden apple's failure characteristics under repeated compressive loadPotravinarstvo Slovak Journal of Food Sciences, 2019
- Prediction of low-visibility events due to fog using ordinal classificationAtmospheric Research, 2018
- Financial time series prediction using hybrids of chaos theory, multi-layer perceptron and multi-objective evolutionary algorithmsSwarm and Evolutionary Computation, 2017
- The comparison of Holt–Winters method and Multiple regression method: A case studyEnergy, 2016
- Multilayer perceptron for GEFCom2014 probabilistic electricity price forecastingInternational Journal of Forecasting, 2016
- A hybrid method based on a new clustering technique and multilayer perceptron neural networks for hourly solar radiation forecastingEnergy Conversion and Management, 2016
- Multiple linear regression, multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signalsHydrological Sciences Journal, 2016
- Pattern-based local linear regression models for short-term load forecastingElectric Power Systems Research, 2016