Predicting COVID-19 Infections in South Africa Using Deep Learning
| dc.contributor.advisor | Ntema, Ratoeba Piet | |
| dc.contributor.advisor | Sonono, Masimba Energy | |
| dc.contributor.advisor | Sidumo, Bonelwa | |
| dc.contributor.author | Ngema, Cebolenkosi | |
| dc.contributor.researchID | 23065176- Ntema, Ratoeba Piet | |
| dc.contributor.researchID | 23756144- Sonono, Masimba Energy | |
| dc.contributor.researchID | 31494498- Sidumo, Bonelwa | |
| dc.date.accessioned | 2024-05-20T10:12:36Z | |
| dc.date.available | 2024-05-20T10:12:36Z | |
| dc.date.issued | 2023 | |
| dc.description | Master of Science in Computer Science, North-West University,vanderbijlpark Campus | en_US |
| dc.description.abstract | In thiswork,themainaimwastoemploydeeplearningtechniquesforpredictingcoro- navirusdisease2019(COVID-19)infectionsinSouthAfrica,withafocusonenhancing the predictivecapacityofCOVID-19virusnewinfections.SincethesurgeofCOVID- 19 infections,therehavebeenconcernsaboutthepotentialeffectsitmighthaveinthe healthcare sector,particularlyinefficientlymanagingresourceavailabilityandallocation. VariousresearchersconducteddifferentstudiestopredictthetransmissionofCOVID-19 infectionsusingtechniquessuchasstatisticalpredictiveanalysis,mathematicalmodel- ing, andmachinelearningapproaches.Studiesusingmathematicalandstatisticalmod- eling hadlimitationsinpredictingfutureinfectionwavesastheywereunabletopredict future wavesofinfections,unlikethoseusingmachinelearning.Hence,themainaimof undertakingthisstudywastoexplorethefeasibilityofemployingaspecificsubsetofma- chine learning,specificallydeeplearning,topredictCOVID-19infectionsinSouthAfrica. The COVID-19datasetusedtobuildthedeeplearningmodelswassourcedfromanopen data repository.Toachievetheaim,thefirststepwastotrainthebasiclongshort-term memory(LSTM),stackedLSTM,andbidirectionalLSTMmodels.LSTM-basedmodels havedemonstratedremarkablecapabilityincapturingtemporaldependencies,whilethe stackedLSTMandthebidirectionalLSTMarchitecturesenhancethiscapabilitybyincor- poratingadditionallayersandbidirectionalinformationflow,respectively.Thenextstep wastoempiricallytestthetrainedmodelsonaCOVID-19realdatasettochecktheirper- formancesbasedontherootmeansquareerror(RMSE).Apersistencemodelthatwas used asabaselinemodeltoevaluateperformancesforthecomplexmodelswasintro- duced. Comparingthepredictionsofthetrainedmodelswiththebaselinemodel,onlythe basic LSTMmodelhadanRMSElowerthanthepersistencemodel.Lastly,identifygaps and challengesinthisstudyandproviderecommendations.Theprimarychallengesand gaps identifiedincludethefactthatthepredictionsweremadeforSouthAfricaoveralland did notcatertosubpopulations.Thisstudyconcludedthattheproposeddeeplearning models exhibitedenhancedpredictabilitycapacityofCOVID-19newinfectionscompared to previousstudiesthatwerereviewed.Additionally,thebasicLSTMmodelwasfoundto be thebestmodelforpredictingCOVID-19infectionsinSouthAfricaasithadthelowest RMSE. | en_US |
| dc.description.thesistype | Masters | en_US |
| dc.identifier.uri | https://orcid.org/0000-0003-3812-049X | |
| dc.identifier.uri | http://hdl.handle.net/10394/42505 | |
| dc.language.iso | en | en_US |
| dc.publisher | North-West University (South Africa) | en_US |
| dc.subject | COVID-19 | en_US |
| dc.subject | Infection | en_US |
| dc.subject | DeepLearning | en_US |
| dc.subject | Prediction | en_US |
| dc.subject | BasicLSTM | en_US |
| dc.subject | StackedLSTM | en_US |
| dc.subject | Bidirectional LSTM. | en_US |
| dc.title | Predicting COVID-19 Infections in South Africa Using Deep Learning | en_US |
| dc.type | Thesis | en_US |