Repository logo
 
Publication

A COVID-19 time series forecasting model based on MLP ANN

2021Conference paper Open access
Simple item page
dc.contributor.authorBorghi, Pedro Henrique
dc.contributor.authorZakordonets, Oleksandr
dc.contributor.authorTeixeira, João Paulo
dc.date.accessioned2022-01-17T11:56:21Z
dc.date.available2022-01-17T11:56:21Z
dc.date.issued2021
dc.description.abstractWith the accelerated spread of COVID-19 worldwide and its potentially fatal effects on human health, the development of a tool that effectively describes and predicts the number of infected cases and deaths over time becomes relevant. This makes it possible for administrative sectors and the population itself to become aware and act more precisely. In this work, a machine learning model based on the multilayer Perceptron artificial neural network structure was used, which effectively predicts the behavior of the series mentioned in up to six days. The model, which is trained with data from 30 countries together in a 20-day context, is assessed using global and local MSE and MAE measures. For the construction of training and test sets, four time series (number of: accumulated infected cases, new cases, accumulated deaths and new deaths) from each country are used, which are started on the day of the first confirmed infection case. In order to soften the sudden transitions between samples, a moving average filter with a window size 3 and a normalization by maximum value were used. It is intended to make the model's predictions available online, collaborating with the fight against the pandemic.pt_PT
dc.description.sponsorshipThis work has been supported by Fundação para a Ciência e Tecnologia within the Project Scope: UIDB/05757/2020.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationBorghi, Pedro Henrique; Zakordonets, Oleksandr; Teixeira, João Paulo (2021). A COVID-19 time series forecasting model based on MLP ANN. In International Conference on ENTERprise Information Systems (CENTERIS), International Conference on Project MANagement (ProjMAN), International Conference on Health and Social Care Information Systems and Technologies (HCist). Procedia Computer Science. ISSN 1877-0509. p. 940-947pt_PT
dc.identifier.doi10.1016/j.procs.2021.01.250pt_PT
dc.identifier.issn1877-0509
dc.identifier.urihttp://hdl.handle.net/10198/24676
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.relationResearch Centre in Digitalization and Intelligent Robotics
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectCOVID-19 Brazil forecastpt_PT
dc.subjectCOVID-19 Italy forecastpt_PT
dc.subjectCOVID-19 worldwide forecastpt_PT
dc.titleA COVID-19 time series forecasting model based on MLP ANNpt_PT
dc.typeconference paper
dspace.entity.typePublication
oaire.awardTitleResearch Centre in Digitalization and Intelligent Robotics
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F05757%2F2020/PT
oaire.citation.endPage947pt_PT
oaire.citation.startPage940pt_PT
oaire.citation.titleProcedia Computer Sciencept_PT
oaire.citation.volume181pt_PT
oaire.fundingStream6817 - DCRRNI ID
person.familyNameTeixeira
person.givenNameJoão Paulo
person.identifier663194
person.identifier.ciencia-id4F15-B322-59B4
person.identifier.orcid0000-0002-6679-5702
person.identifier.ridN-6576-2013
person.identifier.scopus-author-id57069567500
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublication33f4af65-7ddf-46f0-8b44-a7470a8ba2bf
relation.isAuthorOfPublication.latestForDiscovery33f4af65-7ddf-46f0-8b44-a7470a8ba2bf
relation.isProjectOfPublication6e01ddc8-6a82-4131-bca6-84789fa234bd
relation.isProjectOfPublication.latestForDiscovery6e01ddc8-6a82-4131-bca6-84789fa234bd

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Pedro_Covid19_Published.pdf
Size:
1.21 MB
Format:
Adobe Portable Document Format
Download

Collections

ESTiG - Publicações em Proceedings Indexadas à WoS/Scopus