Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia
The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level da...
- Autores:
-
García Balaguera, César
Zhao, Naizhuo
Charland, Katia
Carabali, Mabel
Nsoesie, Elaine
- Tipo de recurso:
- Article of investigation
- Fecha de publicación:
- 2020
- Institución:
- Universidad Cooperativa de Colombia
- Repositorio:
- Repositorio UCC
- Idioma:
- OAI Identifier:
- oai:repository.ucc.edu.co:20.500.12494/33621
- Acceso en línea:
- https://doi.org/10.1371/journal.pntd.0008056
https://hdl.handle.net/20.500.12494/33621
- Palabra clave:
- Fiebre
Dengue
Previsión
Redes neuronales artificales
Dengue fever
Forecasting
Artificial neuronal networks
- Rights
- openAccess
- License
- Atribución
| id |
COOPER2_5ad4ba1bd0853ad16a5adf7ef00b37b0 |
|---|---|
| oai_identifier_str |
oai:repository.ucc.edu.co:20.500.12494/33621 |
| network_acronym_str |
COOPER2 |
| network_name_str |
Repositorio UCC |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia |
| title |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia |
| spellingShingle |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia Fiebre Dengue Previsión Redes neuronales artificales Dengue fever Forecasting Artificial neuronal networks |
| title_short |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia |
| title_full |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia |
| title_fullStr |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia |
| title_full_unstemmed |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia |
| title_sort |
Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in Colombia |
| dc.creator.fl_str_mv |
García Balaguera, César Zhao, Naizhuo Charland, Katia Carabali, Mabel Nsoesie, Elaine |
| dc.contributor.author.none.fl_str_mv |
García Balaguera, César Zhao, Naizhuo Charland, Katia Carabali, Mabel Nsoesie, Elaine |
| dc.subject.spa.fl_str_mv |
Fiebre Dengue Previsión Redes neuronales artificales |
| topic |
Fiebre Dengue Previsión Redes neuronales artificales Dengue fever Forecasting Artificial neuronal networks |
| dc.subject.other.spa.fl_str_mv |
Dengue fever Forecasting Artificial neuronal networks |
| description |
The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level data) and department level in Colombia to predict weekly dengue cases for 12-weeks ahead. A pooled national model based on artificial neural networks (ANN) was also developed and used as a comparator to the RF models. The various predictors included historic dengue cases, satellite-derived estimates for vegetation, precipitation, and air temperature, as well as population counts, income inequality, and education. Our RF model trained on the pooled national data was more accurate for department-specific weekly dengue cases estimation compared to a local model trained only on the department’s data. Additionally, the forecast errors of the national RF model were smaller to those of the national pooled ANN model and were increased with the forecast horizon increasing from one-week-ahead (mean absolute error, MAE: 9.32) to 12-weeks ahead (MAE: 24.56). There was considerable variation in the relative importance of predictors dependent on forecast horizon. The environmental and meteorological predictors were relatively important for short-term dengue forecast horizons while socio-demographic predictors were relevant for longer-term forecast horizons. This study demonstrates the potential of RF in dengue forecasting with a feasible approach of using a national pooled model to forecast at finer spatial scales. Furthermore, including sociodemographic predictors is likely to be helpful in capturing longer-term dengue trends |
| publishDate |
2020 |
| dc.date.issued.none.fl_str_mv |
2020-09-24 |
| dc.date.accessioned.none.fl_str_mv |
2021-03-12T19:43:26Z |
| dc.date.available.none.fl_str_mv |
2021-03-12T19:43:26Z |
| dc.type.none.fl_str_mv |
Artículos Científicos |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.coarversion.none.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| format |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| status_str |
publishedVersion |
| dc.identifier.isbn.spa.fl_str_mv |
1935-2735 |
| dc.identifier.issn.spa.fl_str_mv |
1935-2727 |
| dc.identifier.uri.spa.fl_str_mv |
https://doi.org/10.1371/journal.pntd.0008056 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12494/33621 |
| dc.identifier.bibliographicCitation.spa.fl_str_mv |
Zhao, N., Charland, K., Carabali, M., Nsoesie, E.O., Maheu-Giroux, M., Rees, E., et al. (2020) Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. PLoS Negl Trop Dis 14(9): e0008056. https://doi.org/10.1371/journal.pntd.0008056 |
| identifier_str_mv |
1935-2735 1935-2727 Zhao, N., Charland, K., Carabali, M., Nsoesie, E.O., Maheu-Giroux, M., Rees, E., et al. (2020) Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. PLoS Negl Trop Dis 14(9): e0008056. https://doi.org/10.1371/journal.pntd.0008056 |
| url |
https://doi.org/10.1371/journal.pntd.0008056 https://hdl.handle.net/20.500.12494/33621 |
| dc.relation.ispartofseries.spa.fl_str_mv |
14 |
| dc.relation.isversionof.spa.fl_str_mv |
https://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0008056 |
| dc.relation.seriesnumber.spa.fl_str_mv |
3 |
| dc.relation.ispartofjournal.spa.fl_str_mv |
PLoS Neglected Tropical Disease |
| dc.relation.references.spa.fl_str_mv |
Lambrechts L, Scott TW, Gubler DJ. Consequences of the expanding global distribution of Aedes albopictus for dengue virus transmission. PLoS Neglected Tropical Diseases 2010; 4(5): e646. https://doi. org/10.1371/journal.pntd.0000646 PMID: 20520794 Bhatt S, Gething PW, Brady OJ, Messina JP, Farlow AW, Moyes CLet.al. The global distribution and burden of dengue. Nature 2013; 496:504–507. https://doi.org/10.1038/nature12060 PMID: 23563266 Morin CW, Comrie AC, Ernst K. Climate and dengue transmission: evidence and implications. Environmental Health Perspectives 2013; 121(11–12): 1264. https://doi.org/10.1289/ehp.1306556 PMID: 24058050 Shepard DS, Undurraga EA, Hallasa YA, Stanaway JD. The global economic burden of dengue: a systematic analysis. Lancet Infectious Diseases 2016; 16:935–941. https://doi.org/10.1016/S1473-3099 (16)00146-8 PMID: 27091092 Soyiri IN, Reidpath DD. An overview of health forecasting. Environmental Health and Preventive Medicine 2013; 18(1):1–9. https://doi.org/10.1007/s12199-012-0294-6 PMID: 22949173 RaclozV,RamseyR,TongS,HuW.Surveillanceof denguefevervirus:A reviewof epidemiologicalmodelsandearlywarningsystems.PLoSNeglectedTropicalDiseases 2012;6(5):e1648. https://doi.org/10.1371/journal.pntd.0001648PMID:22629476 GambhirS,MalikSK,KumarY,Thediagnosisof denguedisease:Anevaluationof threemachinelearningapproaches. InternationalJournalof HealthcareInformation SystemsandInformatics2018;13:1–19.https://doi.org/10.4018/ijhisi.2018040101PMID:32913425 NaishS,DaleP,MackenzieJS,McBrideJ, Mengersen K,TongS,Climatechangeanddengue:a criti-calandsystematicreviewof quantitativemodelling approaches. BMCInfectiousDiseases 2014;14:167.https://doi.org/10.1186/1471-2334-14-167PMID:24669859 GharbiM,QuenelP,GustaveJ, CassadouS,RucheGL,GirdaryL, et al.Timeseriesanalysisof den-gueincidencein Guadeloupe, FrenchWestIndies:Forecastingmodelsusingclimatevariablesaspre-dictors.BMCInfectiousDiseases2011;11:166.https://doi.org/10.1186/1471-2334-11-166PMID:21658238 HuW,ClementsA,WilliamsG,TongS,DenguefeverandEl Niño/Southern Oscillationin Queensland,Australia:a timeseriespredictivemodel.Occupational& EnvironmentalMedicine2010;67:307–311 DomNC,HassanAA,LatifZA,IsmailR,Generating temporalmodelusingclimatevariablesforthepre-dictionof denguecasesin SubangJaya,Malasia.AsianPacificJournalof TropicalDisease2013;3:352–361. CortesF, TurchiMartelliCM,ArraesdeAlencarXimenes R,MontarroyosUR,SiqueiraJuniorJB,Gon-c ̧alvesCruzO,et al.Timeseriesanalysisof denguesurveillance datain twoBraziliancities.ActaTro-pica.2018;182:190–7.https://doi.org/10.1016/j.actatropica.2018.03.006PMID:29545150 JohanssonMA,ReichNG,HotaA,Brownstein JS,SantillanaM,Evaluatingtheperformance of infec-tiousdiseaseforecasts: A comparisonof climate-drivenandseasonaldengueforecastsforMexico.Sci-entificReports2016;6:33707.https://doi.org/10.1038/srep33707PMID:27665707 NiuM,WangY,SunS,Li Y,A novelhybriddecomposition-and-ensemblemodelbasedonCEEMDandGWOforshort-termPM2.5concentrationforecasting. Atmospheric Environment2016;134:168–180 ChenM-Y,ChenB-T,A hybridfuzzytimeseriesmodelbasedongranularcomputingforstockpriceforecasting. Information Sciences2015;294:227–241 WangP,ZhangH,QinZ, ZhangG,A novelhybrid-GarchmodelbasedonARIMAandSVMforPM2.5concentrationsforecasting. AtmosphericPollutionResearch2017;8: 850–860 ZhaoN,LiuY,VanosJK,CaoG,Day-of-weekandseasonalpatterns of PM2.5concentrationsovertheUnitedStates:Time-seriesanalysesusingtheProphetprocedure.Atmospheric Environment2018;192:116–127 BreimanL. Statisticalmodeling: thetwocultures(withcommentsanda rejoinderbytheauthor).Statisti-calScience2001;16(3):199–231. MurphyKP.MachineLearning:a probabilisticperspective.MITPress,2012 GuoP,LiuT, ZhangQ,WangL, XiaoJ, ZhangQ,et al.Developinga dengueforecastmodelusingmachinelearning:A casestudyin China.PLoSNeglectedTropicalDiseases2017;11:e0005973.https://doi.org/10.1371/journal.pntd.0005973PMID:29036169 ScavuzzoJM,TruccoF, EspinosaM,TauroCB,AbrilM,Scavuzzo CM,et al.Modelingdenguevectorpopulationusingremotelysenseddataandmachinelearning.ActaTropica2018;185:167–175.https://doi.org/10.1016/j.actatropica.2018.05.003PMID:2977765 AlthouseBM,NgYY,CummingsDAT,Predictionof dengueincidenceusingserachquerysurveillance.PLoSNeglectedTropicalDiseases2011;5:e1258.https://doi.org/10.1371/journal.pntd.0001258PMID:21829744 Laureano-RosarioAE,DuncvanAP,Mendez-LazaroPA,Garcia-RejonJE,Gomez-CarroS,Farfan-AleJ, et al.Applicationof artificial neuralnetworks fordenguefeveroutbreakpredictionsin thenorthwestcoastof Yucatan,MexicoandSanJuan,PuertoRico.TropicalMedicineandInfectiousDisease2018;3:5 RaczkoE,ZagajewskiB,Comparisonof supportvectormachine,randomforestandneuralnetworkclassifiersfortreespeciesclassificationonairbornehyperspectralAPEXimages.EuropeanJournalofRemoteSensing2017;50:144–154. MeyerH,KulhnleinM,AppelhansT, NaussT, Comparisonof fourmachinelearningalgorithmsfortheirapplicabilityin satellite-basedopticalrainfallretrievals.AtmosphericResearch2016;169:424–433. Rodriguez-GalianoV,Sanchez-CastilloM,Chica-Olmo M,Chica-RivasM,Machinelearningpredictivemodelsformineralprospectivity: Anevaluationof neuralnetworks, randomforest,regressiontreesandsupportvectormachines. OreGeologyReviews2015;71:804–818. StatnikovA,WangL, AliferisCF,A comprehensivecomparisonof randomforestsandsupportvectormachinesformicroarray-basedcancerclassification.BMCBioinformatics 2008;9:319.https://doi.org/10.1186/1471-2105-9-319PMID:18647401 NsoesieEO,BeckmanR,MaratheM,LewisB,Predictionof anepidemic curve:A supervisedclassifica-tionapproach. Statisticalcommunicationsin infectiousdiseases.2011;3(1):5.https://doi.org/10.2202/1948-4690.1038PMID:22997545 VasquezP,LoriaA,SanchezF, BarbozaLA,Climate-drivenstatisticalmodelsaseffectivepredictors oflocaldengueincidencein CostaRica:A generalizedadditivemodelandrandomforestapproach.arXiv2019;1907.13095 OlmoguezILG,CatindigMAC,AmongosMFL,LazanAF,Developinga dengueforecastingmodel:Acasestudyin Iligancity.InternationalJournalof AdvancedComputerScienceandApplications2019;10(9):281–286 CarvajalTM,ViacrusisKM,HernandezLFT,HoHT,AmalinDM,WatanabeK,Machinelearningmeth-odsrevealthetemporalpatternof dengueincidenceusingmeteorologicalfactorsin metropolitanManila,Philippines.BMCInfectiousDiseases 2018;18:183.https://doi.org/10.1186/s12879-018-3066-0 PMID:29665781 RehmanNA,KalyanaramanS,AhmadT, PervaizF, SaifU,SubramanianL, Fine-graineddenguefore-castingusingtelephonetriageservices.ScienceAdvances2016;2(7):e1501215.https://doi.org/10.1126/sciadv.1501215 PMID:27419226 FreezeJ, ErraguntlaM,VermaA,Dataintegrationandpredictiveanalysissystemfordiseaseprophy-laxis:Incorporatingdenguefeverforecasts.Proceedingsof the51stHawaiiInternationalConferenceonSystemScience2018;913–922. DinhL, ChowellG,Rothenberg R,Growthscalingfortheearlydynamicsof HIV/AIDSepidemicsin Bra-zilandtheinfluenceof socio-demographicfactors.Journalof TheoreticalBiology2018;442:79–86.https://doi.org/10.1016/j.jtbi.2017.12.030PMID:29330056 ChretienJ-P,RileyS,GeorgeDB,Mathematicalmodelingof theWestAfticaEbolaepidemic. eLIFE2015;4:e09186. https://doi.org/10.7554/eLife.09186PMID:26646185 Cardona-OspinaJA,Villamil-Go ́mezWE,Jimenez-CanizalesCE,Castañeda-Herna ́ndezDM,Rodrı ́-guez-MoralesAJ.Estimatingtheburdenof diseaseandtheeconomiccostattributable to chikungunya,Colombia,2014.Transactions of theRoyalSocietyof TropicalMedicineandHygiene2015;109(12):793–802.https://doi.org/10.1093/trstmh/trv094PMID:26626342 VillarLA,RojasDP,Besada-LombanaS,SartiE.Epidemiologicaltrendsof denguediseasein Colom-bia(2000–2011): a systematicreview.PLoSNeglectedTropicalDiseases2015;9(3):e0003499.https://doi.org/10.1371/journal.pntd.0003499PMID:25790245 OspinaMartinezML,MartinezDuranME,PachecoGarcı ́a OE,BonillaHQ,Pe ́rezNT.,Protocolodevigilanciaensaludpu ́blicaenfermedadporvirusZika.PRO-R02.056.Bogota(Colombia): InstitutoNacionaldeSalud,2017.Available from:http://bvs.minsa.gob.pe/local/MINSA/3449.pdf(lastaccessedDecember 16,2019). BeketovMA,YurchenkoYA,BelevichOE,LiessM,Whatenvironmentalfactorsareimportant determi-nantsof structure,speciesrichness,andabundance of mosquitoassemblages? Journalof MedicalEntomology2010;47:129–139.https://doi.org/10.1603/me09150 PMID:20380292 JoyceRJCMORPH:A methodthatproduces globalprecipitationestimatesfrompassive microwaveandinfrareddataat highspatialandtemporalresolution.Journalof Hydrometeorology2004;5:487–503. KoyadunS,ButrapornP,KittayapongP,Ecologic andsociodemographicriskdeterminantsfordenguetransmissionin urbanareasin Thailand.InterdisciplinaryPerspectivesonInfectiousDiseases2012;2012:907494. https://doi.org/10.1155/2012/907494PMID:23056042 ReiterP,Climatechangeandmosquito-bornedisease.EnvironmentalHealthPerspectives2001;109(supplement1):141–161.https://doi.org/10.1289/ehp.01109s1141PMID:11250812 SoghaierMA,HimattS,OsmanKE,OkouedSI,SeidahmedOE,BeattyME,et al.,Cross-sectionalcommunity-basedstudyof thesocio-demographicfactorsassociatedwiththeprevalence of dengueintheeasternpartof Sudanin 2011.BMCPublicHealth2015;15:558.https://doi.org/10.1186/s12889-015-1913-0 PMID:26084275 KannanMaharajanM,RajiahK,SingcoBelotindosJA,BasesMS.Socialdeterminantspredictingtheknowledge,attitudes,andpracticesof womentowardzikavirusinfectionFrontiers in PublicHealth2020;8:170.https://doi.org/10.3389/fpubh.2020.00170PMID:32582602 CouseQuinnS,KumarS.Healthinequalitiesandinfectiousdiseaseepidemics:A challengeforglobalhealthsecurity.BiosecurityandBioterrorism:Biodefense Srategy,Practice,andScience2014;12(5):263–273. BreimanL, Randomforests.Machinelearning2001;45(1):5–32. HulmeM,NewM.Dependenceof large-scaleprecipitationclimatologiesontemporalandspatialsam-pling.Journalof Climate,1997;10:1099–1113, PapacharalampousGA,TyralisH,Evaluationof randomforestsandprophetfordailystreamflowfore-casting.Advancesin Geosciences2018;45:201–208. LuL, LinH,TianL, YangW,SunJ, LiuQ,Timeseriesanalysisof denguefeverandweatherin Guang-zhou,China,BMCPublicHealth2009;9:395.https://doi.org/10.1186/1471-2458-9-395PMID:19860867 ChenS-C.LiaoC-M,ChioC-P,ChouH-H,YouS-H,ChengY-H,laggedtemperature effectwithmos-quitotransmissionpotentialexplainsdenguevariabilityin southernTaiwan:Insightsfroma statisticalanalysis.Scienceof TheTotalEnvironment 2010;408(19):469–4075. CheongYL,BurkartK,LeitaoPJ,LakesT, Assessingweathereffectsondenguediseasein Malaysia,InternationalJournalof EnvironmentalResearchandPublicHealth2013;10(12):6319–6334. https://doi.org/10.3390/ijerph10126319PMID:24287855 ChangK,ChenC-D,ShihC-M,LeeT-C,WuM-T,WuD-C,et al.,Time-lagginginterplayeffectandexcessriskof meteorological/mosquitoparametersandpetrochemicalgasexplosionondengueinci-dence.Scientificreports2016;6:35028.https://doi.org/10.1038/srep35028PMID:27733774 ChenY,OngJHY,RajarethinamJ, YapG,NgLC,CookAR.Neighbourhoodlevelreal-timeforecastingof denguecasesin tropicalurbanSingapore. BMCMedicine2018;16(1):129.https://doi.org/10.1186/s12916-018-1108-5PMID:30078378 EastinMD,DelmelleE,CasasI, WexlerJ, SelfC,Intra-andinterseasonalautoregressivepredictionofdengueoutbreaks usinglocalweatherandregionalclimatefora tropicalenvironment in Colombia.TheAmericanJournalof TropicalMedicineandHygiene2014;91(3):598–610.https://doi.org/10.4269/ajtmh.13-0303PMID:24957546 BostanN,JavedS,AmenN,EqaniSAMAS,TahirF, BokhariH,Denguefevervirusin Pakistan:effectsof seasonalpatternandtemperature changeondistributionof vectorandvirus.Reviewsin MedicalVirology2017;27(1):e1899 OidtmanRJ,LaiS,HuangZ, YangJ, SirajAS,ReinerRC,et al.,Inter-annual variationin seasonalden-gueepidemicsdrivenbymultipleinteractingfactorsin Guangzhou,China,NatureCommunications2019;10:1148. https://doi.org/10.1038/s41467-019-09035-xPMID:30850598 HastieT, Tibshirani R,FriedmanJ. Theelementsof statistical learning.Spring,Berlin,2008 LiawA,WienerM.Breiman andCulter’srandomforestsforclassificationandregression.2018.Avail-ablefrom:https://cran.r-project.org/web/packages/randomForest/randomForest.pdf(lastaccessedMay7, 2020). PengZ, LetuH,WangT, ShiC,ZhaoC,TanaG,ZhaoN,DaiT, TangR,ShangH,ShiJ, ChenL. Esti-mationof shortwavesolarradiationusingtheartificialneuralnetworkfromHimawari-8satelliteimageryoverChina.Journalof QuantitativeSpectroscopyandRadiativeTransfer2020;240:106672. Hyndman RJ,KhandakarY.Automatictimeseriesforecasting: TheforecastpackageforR.JournalofStatisticalSoftware2008;27:1–22. ReichNG,LesslerJ, SakrejdaK,LauerSA,Iamsirithaworn S,CummingsDAT.Casestudyin evaluat-ingtimeseriespredictionmodelsusingtherelativemeanabsoluteerror.TheAmericanStatistician2016;70:285–292. https://doi.org/10.1080/00031305.2016.1148631PMID:28138198 LiuY,CaoG,ZhaoN,MulliganK,YeX.Improveground-levelPM2.5concentrationmappingusingarandomforests-basedgeostatisticalapproach. EnvironmentalPollution2018;235:272–282.https://doi.org/10.1016/j.envpol.2017.12.070PMID:29291527 GrziwotzF, StraußJF,HsiehC-h,TelschowA.Empiricaldynamicmodelling identifiesdifferentresponses ofAedesPolynesiensissubpopulationsto naturalenvironmentalvariables. ScientificReports2018;8: 16768.https://doi.org/10.1038/s41598-018-34972-wPMID:30425277 da Cruz Ferreira DA,DegenerCM,deAlmeidaMarques-ToledoC,BendatiMM,FetzerLO,TeixeiraCP,EirasAE.Meteorological variablesandmosquitomonitoringaregoodpredictorsforinfestationtrendsof Aedesaegypti,thevectorof dengue,chikungunyaandZika.ParasitesVectors2017;10:78.https://doi.org/10.1186/s13071-017-2025-8PMID:28193291 ManicaM,Filipponi F, D’Alessandro A,ScretiA,NetelerM,RosàR,et al.SpatialandTemporal HotSpotsofAedesalbopictusAbundance insideandoutsidea SouthEuropeanMetropolitanArea.PLoSNeglectedTropicalDiseases2016;10(6):e0004758.https://doi.org/10.1371/journal.pntd.0004758PMID:27333276 MulliganK,DixonJ, SinnC-LJ, ElliottSJ.Is denguea diseaseof poverty?A systematicreview.Patho-gensandGlobalHealth2015;109(1):10–18.https://doi.org/10.1179/2047773214Y.0000000168PMID:25546339 Tapia-ConyerR,Me ́ndez-Galva ́n JF,Gallardo-Rinco ́n H.Thegrowingburdenof denguein LatinAmer-ica.Journalof ClinicalVirology2009;46:S3–S6.https://doi.org/10.1016/S1386-6532(09)70286-0PMID:19800563 AdamsEA,BoatengGO,AmoyawJA.Socioeconomic anddemographicpredictors of potablewaterandsanitationaccessin Ghana.SocialIndicatorsResearch2016;126(2):673–687. deJanvryA,SadouletE.Growth,poverty,andinequalityin LatinAmerica:A causalanalysis,1970–94.Thereviewof IncomeandWealth2000;46(3):267–287. Najafabadi MM,VillanustreF, KhoshgoftaarTM,SeliyaN,WaldR,MuharemagicE.Deeplearningapplicationsandchallenges in bigdataanalytics.Journalof BigData2015;2:1 OngJ, LiuX,RajarethinamJ, KokSY,LiangS,TangCS,et al.,Mappingdengueriskin Singaporeusingrandomforest.PLoSNeglectedTropicalDiseases2018;12(6):e0006587.https://doi.org/10.1371/journal.pntd.0006587PMID:29912940 WilliamsRJ,ZipserD,A learningalgorithmforcontinually runningfullyrecurrentneuralnetworks.Neu-ralComputation1989;1(2):270–280. |
| dc.rights.license.none.fl_str_mv |
Atribución |
| dc.rights.accessrights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
Atribución http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.spa.fl_str_mv |
1-16 |
| dc.coverage.temporal.spa.fl_str_mv |
14-9 |
| dc.publisher.spa.fl_str_mv |
Universidad Cooperativa de Colombia, Facultad de Ciencias de la Salud, Medicina, Villavicencio |
| dc.publisher.program.spa.fl_str_mv |
Medicina |
| dc.publisher.place.spa.fl_str_mv |
Villavicencio |
| institution |
Universidad Cooperativa de Colombia |
| bitstream.url.fl_str_mv |
https://repository.ucc.edu.co/bitstreams/af7dac0a-9ccd-45ea-aef5-6d4938635d14/download https://repository.ucc.edu.co/bitstreams/b837de38-bd73-4ee9-936b-f4b2ef35d1ae/download https://repository.ucc.edu.co/bitstreams/15336c0b-e0e7-4156-89be-cf3542a1f074/download https://repository.ucc.edu.co/bitstreams/db90c7ef-a570-4136-8e0f-c6b0259da24f/download https://repository.ucc.edu.co/bitstreams/685ff642-3555-4317-b17e-2d7182168ee0/download https://repository.ucc.edu.co/bitstreams/5ca30d49-6970-454d-acc0-ff58519c0306/download https://repository.ucc.edu.co/bitstreams/e077fe3f-b45d-4e6b-984c-f869e27ba6cd/download |
| bitstream.checksum.fl_str_mv |
3bce4f7ab09dfc588f126e1e36e98a45 b2ce7c8ff6451109859fcef3a1f70278 0e51a8f31ddd7ac34eddb9ee0083128e 60b17a273fb2e3be9688997747879ad9 910a90cb4b18964de4b22960aff8b240 881ade4dffae608891afa318aa4b88a2 2e8d955a5ccabe20f367d7568352647f |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional Universidad Cooperativa de Colombia |
| repository.mail.fl_str_mv |
bdigital@metabiblioteca.com |
| _version_ |
1811565662647091200 |
| spelling |
García Balaguera, CésarZhao, NaizhuoCharland, KatiaCarabali, MabelNsoesie, Elaine14-92021-03-12T19:43:26Z2021-03-12T19:43:26Z2020-09-241935-27351935-2727https://doi.org/10.1371/journal.pntd.0008056https://hdl.handle.net/20.500.12494/33621Zhao, N., Charland, K., Carabali, M., Nsoesie, E.O., Maheu-Giroux, M., Rees, E., et al. (2020) Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. PLoS Negl Trop Dis 14(9): e0008056. https://doi.org/10.1371/journal.pntd.0008056The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level data) and department level in Colombia to predict weekly dengue cases for 12-weeks ahead. A pooled national model based on artificial neural networks (ANN) was also developed and used as a comparator to the RF models. The various predictors included historic dengue cases, satellite-derived estimates for vegetation, precipitation, and air temperature, as well as population counts, income inequality, and education. Our RF model trained on the pooled national data was more accurate for department-specific weekly dengue cases estimation compared to a local model trained only on the department’s data. Additionally, the forecast errors of the national RF model were smaller to those of the national pooled ANN model and were increased with the forecast horizon increasing from one-week-ahead (mean absolute error, MAE: 9.32) to 12-weeks ahead (MAE: 24.56). There was considerable variation in the relative importance of predictors dependent on forecast horizon. The environmental and meteorological predictors were relatively important for short-term dengue forecast horizons while socio-demographic predictors were relevant for longer-term forecast horizons. This study demonstrates the potential of RF in dengue forecasting with a feasible approach of using a national pooled model to forecast at finer spatial scales. Furthermore, including sociodemographic predictors is likely to be helpful in capturing longer-term dengue trends0000584894201005042460https://orcid.org/0000-0002-0750-5541COL0096201cesar.garcia@campusucc.edu.cohttps://scholar.google.es/citations?user=CZo1nV4AAAAJ&hl=es1-16Universidad Cooperativa de Colombia, Facultad de Ciencias de la Salud, Medicina, VillavicencioMedicinaVillavicencio14https://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.00080563PLoS Neglected Tropical DiseaseLambrechts L, Scott TW, Gubler DJ. Consequences of the expanding global distribution of Aedes albopictus for dengue virus transmission. PLoS Neglected Tropical Diseases 2010; 4(5): e646. https://doi. org/10.1371/journal.pntd.0000646 PMID: 20520794Bhatt S, Gething PW, Brady OJ, Messina JP, Farlow AW, Moyes CLet.al. The global distribution and burden of dengue. Nature 2013; 496:504–507. https://doi.org/10.1038/nature12060 PMID: 23563266Morin CW, Comrie AC, Ernst K. Climate and dengue transmission: evidence and implications. Environmental Health Perspectives 2013; 121(11–12): 1264. https://doi.org/10.1289/ehp.1306556 PMID: 24058050Shepard DS, Undurraga EA, Hallasa YA, Stanaway JD. The global economic burden of dengue: a systematic analysis. Lancet Infectious Diseases 2016; 16:935–941. https://doi.org/10.1016/S1473-3099 (16)00146-8 PMID: 27091092Soyiri IN, Reidpath DD. An overview of health forecasting. Environmental Health and Preventive Medicine 2013; 18(1):1–9. https://doi.org/10.1007/s12199-012-0294-6 PMID: 22949173RaclozV,RamseyR,TongS,HuW.Surveillanceof denguefevervirus:A reviewof epidemiologicalmodelsandearlywarningsystems.PLoSNeglectedTropicalDiseases 2012;6(5):e1648. https://doi.org/10.1371/journal.pntd.0001648PMID:22629476GambhirS,MalikSK,KumarY,Thediagnosisof denguedisease:Anevaluationof threemachinelearningapproaches. InternationalJournalof HealthcareInformation SystemsandInformatics2018;13:1–19.https://doi.org/10.4018/ijhisi.2018040101PMID:32913425NaishS,DaleP,MackenzieJS,McBrideJ, Mengersen K,TongS,Climatechangeanddengue:a criti-calandsystematicreviewof quantitativemodelling approaches. BMCInfectiousDiseases 2014;14:167.https://doi.org/10.1186/1471-2334-14-167PMID:24669859GharbiM,QuenelP,GustaveJ, CassadouS,RucheGL,GirdaryL, et al.Timeseriesanalysisof den-gueincidencein Guadeloupe, FrenchWestIndies:Forecastingmodelsusingclimatevariablesaspre-dictors.BMCInfectiousDiseases2011;11:166.https://doi.org/10.1186/1471-2334-11-166PMID:21658238HuW,ClementsA,WilliamsG,TongS,DenguefeverandEl Niño/Southern Oscillationin Queensland,Australia:a timeseriespredictivemodel.Occupational& EnvironmentalMedicine2010;67:307–311DomNC,HassanAA,LatifZA,IsmailR,Generating temporalmodelusingclimatevariablesforthepre-dictionof denguecasesin SubangJaya,Malasia.AsianPacificJournalof TropicalDisease2013;3:352–361.CortesF, TurchiMartelliCM,ArraesdeAlencarXimenes R,MontarroyosUR,SiqueiraJuniorJB,Gon-c ̧alvesCruzO,et al.Timeseriesanalysisof denguesurveillance datain twoBraziliancities.ActaTro-pica.2018;182:190–7.https://doi.org/10.1016/j.actatropica.2018.03.006PMID:29545150JohanssonMA,ReichNG,HotaA,Brownstein JS,SantillanaM,Evaluatingtheperformance of infec-tiousdiseaseforecasts: A comparisonof climate-drivenandseasonaldengueforecastsforMexico.Sci-entificReports2016;6:33707.https://doi.org/10.1038/srep33707PMID:27665707NiuM,WangY,SunS,Li Y,A novelhybriddecomposition-and-ensemblemodelbasedonCEEMDandGWOforshort-termPM2.5concentrationforecasting. Atmospheric Environment2016;134:168–180ChenM-Y,ChenB-T,A hybridfuzzytimeseriesmodelbasedongranularcomputingforstockpriceforecasting. Information Sciences2015;294:227–241WangP,ZhangH,QinZ, ZhangG,A novelhybrid-GarchmodelbasedonARIMAandSVMforPM2.5concentrationsforecasting. AtmosphericPollutionResearch2017;8: 850–860ZhaoN,LiuY,VanosJK,CaoG,Day-of-weekandseasonalpatterns of PM2.5concentrationsovertheUnitedStates:Time-seriesanalysesusingtheProphetprocedure.Atmospheric Environment2018;192:116–127BreimanL. Statisticalmodeling: thetwocultures(withcommentsanda rejoinderbytheauthor).Statisti-calScience2001;16(3):199–231.MurphyKP.MachineLearning:a probabilisticperspective.MITPress,2012GuoP,LiuT, ZhangQ,WangL, XiaoJ, ZhangQ,et al.Developinga dengueforecastmodelusingmachinelearning:A casestudyin China.PLoSNeglectedTropicalDiseases2017;11:e0005973.https://doi.org/10.1371/journal.pntd.0005973PMID:29036169ScavuzzoJM,TruccoF, EspinosaM,TauroCB,AbrilM,Scavuzzo CM,et al.Modelingdenguevectorpopulationusingremotelysenseddataandmachinelearning.ActaTropica2018;185:167–175.https://doi.org/10.1016/j.actatropica.2018.05.003PMID:2977765AlthouseBM,NgYY,CummingsDAT,Predictionof dengueincidenceusingserachquerysurveillance.PLoSNeglectedTropicalDiseases2011;5:e1258.https://doi.org/10.1371/journal.pntd.0001258PMID:21829744Laureano-RosarioAE,DuncvanAP,Mendez-LazaroPA,Garcia-RejonJE,Gomez-CarroS,Farfan-AleJ, et al.Applicationof artificial neuralnetworks fordenguefeveroutbreakpredictionsin thenorthwestcoastof Yucatan,MexicoandSanJuan,PuertoRico.TropicalMedicineandInfectiousDisease2018;3:5RaczkoE,ZagajewskiB,Comparisonof supportvectormachine,randomforestandneuralnetworkclassifiersfortreespeciesclassificationonairbornehyperspectralAPEXimages.EuropeanJournalofRemoteSensing2017;50:144–154.MeyerH,KulhnleinM,AppelhansT, NaussT, Comparisonof fourmachinelearningalgorithmsfortheirapplicabilityin satellite-basedopticalrainfallretrievals.AtmosphericResearch2016;169:424–433.Rodriguez-GalianoV,Sanchez-CastilloM,Chica-Olmo M,Chica-RivasM,Machinelearningpredictivemodelsformineralprospectivity: Anevaluationof neuralnetworks, randomforest,regressiontreesandsupportvectormachines. OreGeologyReviews2015;71:804–818.StatnikovA,WangL, AliferisCF,A comprehensivecomparisonof randomforestsandsupportvectormachinesformicroarray-basedcancerclassification.BMCBioinformatics 2008;9:319.https://doi.org/10.1186/1471-2105-9-319PMID:18647401NsoesieEO,BeckmanR,MaratheM,LewisB,Predictionof anepidemic curve:A supervisedclassifica-tionapproach. Statisticalcommunicationsin infectiousdiseases.2011;3(1):5.https://doi.org/10.2202/1948-4690.1038PMID:22997545VasquezP,LoriaA,SanchezF, BarbozaLA,Climate-drivenstatisticalmodelsaseffectivepredictors oflocaldengueincidencein CostaRica:A generalizedadditivemodelandrandomforestapproach.arXiv2019;1907.13095OlmoguezILG,CatindigMAC,AmongosMFL,LazanAF,Developinga dengueforecastingmodel:Acasestudyin Iligancity.InternationalJournalof AdvancedComputerScienceandApplications2019;10(9):281–286CarvajalTM,ViacrusisKM,HernandezLFT,HoHT,AmalinDM,WatanabeK,Machinelearningmeth-odsrevealthetemporalpatternof dengueincidenceusingmeteorologicalfactorsin metropolitanManila,Philippines.BMCInfectiousDiseases 2018;18:183.https://doi.org/10.1186/s12879-018-3066-0 PMID:29665781RehmanNA,KalyanaramanS,AhmadT, PervaizF, SaifU,SubramanianL, Fine-graineddenguefore-castingusingtelephonetriageservices.ScienceAdvances2016;2(7):e1501215.https://doi.org/10.1126/sciadv.1501215 PMID:27419226FreezeJ, ErraguntlaM,VermaA,Dataintegrationandpredictiveanalysissystemfordiseaseprophy-laxis:Incorporatingdenguefeverforecasts.Proceedingsof the51stHawaiiInternationalConferenceonSystemScience2018;913–922.DinhL, ChowellG,Rothenberg R,Growthscalingfortheearlydynamicsof HIV/AIDSepidemicsin Bra-zilandtheinfluenceof socio-demographicfactors.Journalof TheoreticalBiology2018;442:79–86.https://doi.org/10.1016/j.jtbi.2017.12.030PMID:29330056ChretienJ-P,RileyS,GeorgeDB,Mathematicalmodelingof theWestAfticaEbolaepidemic. eLIFE2015;4:e09186. https://doi.org/10.7554/eLife.09186PMID:26646185Cardona-OspinaJA,Villamil-Go ́mezWE,Jimenez-CanizalesCE,Castañeda-Herna ́ndezDM,Rodrı ́-guez-MoralesAJ.Estimatingtheburdenof diseaseandtheeconomiccostattributable to chikungunya,Colombia,2014.Transactions of theRoyalSocietyof TropicalMedicineandHygiene2015;109(12):793–802.https://doi.org/10.1093/trstmh/trv094PMID:26626342VillarLA,RojasDP,Besada-LombanaS,SartiE.Epidemiologicaltrendsof denguediseasein Colom-bia(2000–2011): a systematicreview.PLoSNeglectedTropicalDiseases2015;9(3):e0003499.https://doi.org/10.1371/journal.pntd.0003499PMID:25790245OspinaMartinezML,MartinezDuranME,PachecoGarcı ́a OE,BonillaHQ,Pe ́rezNT.,Protocolodevigilanciaensaludpu ́blicaenfermedadporvirusZika.PRO-R02.056.Bogota(Colombia): InstitutoNacionaldeSalud,2017.Available from:http://bvs.minsa.gob.pe/local/MINSA/3449.pdf(lastaccessedDecember 16,2019).BeketovMA,YurchenkoYA,BelevichOE,LiessM,Whatenvironmentalfactorsareimportant determi-nantsof structure,speciesrichness,andabundance of mosquitoassemblages? Journalof MedicalEntomology2010;47:129–139.https://doi.org/10.1603/me09150 PMID:20380292JoyceRJCMORPH:A methodthatproduces globalprecipitationestimatesfrompassive microwaveandinfrareddataat highspatialandtemporalresolution.Journalof Hydrometeorology2004;5:487–503.KoyadunS,ButrapornP,KittayapongP,Ecologic andsociodemographicriskdeterminantsfordenguetransmissionin urbanareasin Thailand.InterdisciplinaryPerspectivesonInfectiousDiseases2012;2012:907494. https://doi.org/10.1155/2012/907494PMID:23056042ReiterP,Climatechangeandmosquito-bornedisease.EnvironmentalHealthPerspectives2001;109(supplement1):141–161.https://doi.org/10.1289/ehp.01109s1141PMID:11250812SoghaierMA,HimattS,OsmanKE,OkouedSI,SeidahmedOE,BeattyME,et al.,Cross-sectionalcommunity-basedstudyof thesocio-demographicfactorsassociatedwiththeprevalence of dengueintheeasternpartof Sudanin 2011.BMCPublicHealth2015;15:558.https://doi.org/10.1186/s12889-015-1913-0 PMID:26084275KannanMaharajanM,RajiahK,SingcoBelotindosJA,BasesMS.Socialdeterminantspredictingtheknowledge,attitudes,andpracticesof womentowardzikavirusinfectionFrontiers in PublicHealth2020;8:170.https://doi.org/10.3389/fpubh.2020.00170PMID:32582602CouseQuinnS,KumarS.Healthinequalitiesandinfectiousdiseaseepidemics:A challengeforglobalhealthsecurity.BiosecurityandBioterrorism:Biodefense Srategy,Practice,andScience2014;12(5):263–273.BreimanL, Randomforests.Machinelearning2001;45(1):5–32.HulmeM,NewM.Dependenceof large-scaleprecipitationclimatologiesontemporalandspatialsam-pling.Journalof Climate,1997;10:1099–1113,PapacharalampousGA,TyralisH,Evaluationof randomforestsandprophetfordailystreamflowfore-casting.Advancesin Geosciences2018;45:201–208.LuL, LinH,TianL, YangW,SunJ, LiuQ,Timeseriesanalysisof denguefeverandweatherin Guang-zhou,China,BMCPublicHealth2009;9:395.https://doi.org/10.1186/1471-2458-9-395PMID:19860867ChenS-C.LiaoC-M,ChioC-P,ChouH-H,YouS-H,ChengY-H,laggedtemperature effectwithmos-quitotransmissionpotentialexplainsdenguevariabilityin southernTaiwan:Insightsfroma statisticalanalysis.Scienceof TheTotalEnvironment 2010;408(19):469–4075.CheongYL,BurkartK,LeitaoPJ,LakesT, Assessingweathereffectsondenguediseasein Malaysia,InternationalJournalof EnvironmentalResearchandPublicHealth2013;10(12):6319–6334. https://doi.org/10.3390/ijerph10126319PMID:24287855ChangK,ChenC-D,ShihC-M,LeeT-C,WuM-T,WuD-C,et al.,Time-lagginginterplayeffectandexcessriskof meteorological/mosquitoparametersandpetrochemicalgasexplosionondengueinci-dence.Scientificreports2016;6:35028.https://doi.org/10.1038/srep35028PMID:27733774ChenY,OngJHY,RajarethinamJ, YapG,NgLC,CookAR.Neighbourhoodlevelreal-timeforecastingof denguecasesin tropicalurbanSingapore. BMCMedicine2018;16(1):129.https://doi.org/10.1186/s12916-018-1108-5PMID:30078378EastinMD,DelmelleE,CasasI, WexlerJ, SelfC,Intra-andinterseasonalautoregressivepredictionofdengueoutbreaks usinglocalweatherandregionalclimatefora tropicalenvironment in Colombia.TheAmericanJournalof TropicalMedicineandHygiene2014;91(3):598–610.https://doi.org/10.4269/ajtmh.13-0303PMID:24957546BostanN,JavedS,AmenN,EqaniSAMAS,TahirF, BokhariH,Denguefevervirusin Pakistan:effectsof seasonalpatternandtemperature changeondistributionof vectorandvirus.Reviewsin MedicalVirology2017;27(1):e1899OidtmanRJ,LaiS,HuangZ, YangJ, SirajAS,ReinerRC,et al.,Inter-annual variationin seasonalden-gueepidemicsdrivenbymultipleinteractingfactorsin Guangzhou,China,NatureCommunications2019;10:1148. https://doi.org/10.1038/s41467-019-09035-xPMID:30850598HastieT, Tibshirani R,FriedmanJ. Theelementsof statistical learning.Spring,Berlin,2008LiawA,WienerM.Breiman andCulter’srandomforestsforclassificationandregression.2018.Avail-ablefrom:https://cran.r-project.org/web/packages/randomForest/randomForest.pdf(lastaccessedMay7, 2020).PengZ, LetuH,WangT, ShiC,ZhaoC,TanaG,ZhaoN,DaiT, TangR,ShangH,ShiJ, ChenL. Esti-mationof shortwavesolarradiationusingtheartificialneuralnetworkfromHimawari-8satelliteimageryoverChina.Journalof QuantitativeSpectroscopyandRadiativeTransfer2020;240:106672.Hyndman RJ,KhandakarY.Automatictimeseriesforecasting: TheforecastpackageforR.JournalofStatisticalSoftware2008;27:1–22.ReichNG,LesslerJ, SakrejdaK,LauerSA,Iamsirithaworn S,CummingsDAT.Casestudyin evaluat-ingtimeseriespredictionmodelsusingtherelativemeanabsoluteerror.TheAmericanStatistician2016;70:285–292. https://doi.org/10.1080/00031305.2016.1148631PMID:28138198LiuY,CaoG,ZhaoN,MulliganK,YeX.Improveground-levelPM2.5concentrationmappingusingarandomforests-basedgeostatisticalapproach. EnvironmentalPollution2018;235:272–282.https://doi.org/10.1016/j.envpol.2017.12.070PMID:29291527GrziwotzF, StraußJF,HsiehC-h,TelschowA.Empiricaldynamicmodelling identifiesdifferentresponses ofAedesPolynesiensissubpopulationsto naturalenvironmentalvariables. ScientificReports2018;8: 16768.https://doi.org/10.1038/s41598-018-34972-wPMID:30425277da Cruz Ferreira DA,DegenerCM,deAlmeidaMarques-ToledoC,BendatiMM,FetzerLO,TeixeiraCP,EirasAE.Meteorological variablesandmosquitomonitoringaregoodpredictorsforinfestationtrendsof Aedesaegypti,thevectorof dengue,chikungunyaandZika.ParasitesVectors2017;10:78.https://doi.org/10.1186/s13071-017-2025-8PMID:28193291ManicaM,Filipponi F, D’Alessandro A,ScretiA,NetelerM,RosàR,et al.SpatialandTemporal HotSpotsofAedesalbopictusAbundance insideandoutsidea SouthEuropeanMetropolitanArea.PLoSNeglectedTropicalDiseases2016;10(6):e0004758.https://doi.org/10.1371/journal.pntd.0004758PMID:27333276MulliganK,DixonJ, SinnC-LJ, ElliottSJ.Is denguea diseaseof poverty?A systematicreview.Patho-gensandGlobalHealth2015;109(1):10–18.https://doi.org/10.1179/2047773214Y.0000000168PMID:25546339Tapia-ConyerR,Me ́ndez-Galva ́n JF,Gallardo-Rinco ́n H.Thegrowingburdenof denguein LatinAmer-ica.Journalof ClinicalVirology2009;46:S3–S6.https://doi.org/10.1016/S1386-6532(09)70286-0PMID:19800563AdamsEA,BoatengGO,AmoyawJA.Socioeconomic anddemographicpredictors of potablewaterandsanitationaccessin Ghana.SocialIndicatorsResearch2016;126(2):673–687.deJanvryA,SadouletE.Growth,poverty,andinequalityin LatinAmerica:A causalanalysis,1970–94.Thereviewof IncomeandWealth2000;46(3):267–287.Najafabadi MM,VillanustreF, KhoshgoftaarTM,SeliyaN,WaldR,MuharemagicE.Deeplearningapplicationsandchallenges in bigdataanalytics.Journalof BigData2015;2:1OngJ, LiuX,RajarethinamJ, KokSY,LiangS,TangCS,et al.,Mappingdengueriskin Singaporeusingrandomforest.PLoSNeglectedTropicalDiseases2018;12(6):e0006587.https://doi.org/10.1371/journal.pntd.0006587PMID:29912940WilliamsRJ,ZipserD,A learningalgorithmforcontinually runningfullyrecurrentneuralnetworks.Neu-ralComputation1989;1(2):270–280.FiebreDenguePrevisiónRedes neuronales artificalesDengue feverForecastingArtificial neuronal networksMachine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-nationalscales in ColombiaArtículos Científicoshttp://purl.org/coar/resource_type/c_2df8fbb1http://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionAtribucióninfo:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2PublicationLICENSElicense.txtlicense.txttext/plain; charset=utf-84334https://repository.ucc.edu.co/bitstreams/af7dac0a-9ccd-45ea-aef5-6d4938635d14/download3bce4f7ab09dfc588f126e1e36e98a45MD53ORIGINALMACHINE LEARNING FORECASTING 2020.pdfMACHINE LEARNING FORECASTING 2020.pdfArtículoapplication/pdf1552130https://repository.ucc.edu.co/bitstreams/b837de38-bd73-4ee9-936b-f4b2ef35d1ae/downloadb2ce7c8ff6451109859fcef3a1f70278MD51Licencia de uso RI MACHINE FORECASTING.pdfLicencia de uso RI MACHINE FORECASTING.pdfLicencia de usoapplication/pdf211691https://repository.ucc.edu.co/bitstreams/15336c0b-e0e7-4156-89be-cf3542a1f074/download0e51a8f31ddd7ac34eddb9ee0083128eMD52THUMBNAILMACHINE LEARNING FORECASTING 2020.pdf.jpgMACHINE LEARNING FORECASTING 2020.pdf.jpgGenerated Thumbnailimage/jpeg5961https://repository.ucc.edu.co/bitstreams/db90c7ef-a570-4136-8e0f-c6b0259da24f/download60b17a273fb2e3be9688997747879ad9MD54Licencia de uso RI MACHINE FORECASTING.pdf.jpgLicencia de uso RI MACHINE FORECASTING.pdf.jpgGenerated Thumbnailimage/jpeg5118https://repository.ucc.edu.co/bitstreams/685ff642-3555-4317-b17e-2d7182168ee0/download910a90cb4b18964de4b22960aff8b240MD55TEXTMACHINE LEARNING FORECASTING 2020.pdf.txtMACHINE LEARNING FORECASTING 2020.pdf.txtExtracted texttext/plain65578https://repository.ucc.edu.co/bitstreams/5ca30d49-6970-454d-acc0-ff58519c0306/download881ade4dffae608891afa318aa4b88a2MD56Licencia de uso RI MACHINE FORECASTING.pdf.txtLicencia de uso RI MACHINE FORECASTING.pdf.txtExtracted texttext/plain5953https://repository.ucc.edu.co/bitstreams/e077fe3f-b45d-4e6b-984c-f869e27ba6cd/download2e8d955a5ccabe20f367d7568352647fMD5720.500.12494/33621oai:repository.ucc.edu.co:20.500.12494/336212024-08-10 22:47:54.003restrictedhttps://repository.ucc.edu.coRepositorio Institucional Universidad Cooperativa de Colombiabdigital@metabiblioteca.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 |