Repository logo
 
Publication

Prediction performance of separate collection of packaging waste yields using support vector machines

2019Journal article Restricted access
Simple item page
dc.contributor.authorSousa, Vítor
dc.contributor.authorMeireles, I.
dc.contributor.authorOliveira, Verónica
dc.contributor.authorFerreira, Célia
dc.date.accessioned2020-03-05T14:48:48Z
dc.date.available2020-03-05T14:48:48Z
dc.date.issued2019
dc.date.updated2020-02-29T10:54:49Z
dc.description.abstractUnderstanding the drivers underlying waste production in general, and source-segregated waste in particular, is of utmost importance for waste managers. This work aims at evaluating the performance of support vector machines (SVM) models in the prediction of separate collection yields for packaging waste at municipal level. Two SVM models were developed for a case study of 42 municipalities simultaneously serviced by separate collection of packaging waste and by unsorted waste collection. The “SVM-fxed” model used a fxed set of 5 variables to predict collection yields, whereas the “SVM-optimal” model chose from a pool of 14 variables those that optimized performance, using a genetic algorithm. These SVM models were compared with 3 traditional regression models: the ordinary least square linear (OLS-L), the ordinary least square non-linear (OLS-NL) and robust regression. The robust regression model was further compared against the other regression models in order to assess the infuence of the dataset outliers on the model performance. The coefcient of determination, R2 , was used to evaluate the performance of these models. The highest performance was attained by the SVM-optimal model (R2=0.918), compared to the SVM-fxed model (R2=0.670). The performance of the SVM-optimal model was 42% higher than the best performing regression model, the OLS-NL model (R2=0.646). The diferences in performance among the 3 regression models are small (circa 3%), whereas the exclusion of outliers improved their performance by 13%, indicating that outliers impacted more on performance than the type of traditional regression technique used. The results demonstrate that SVM model can be a viable alternative for prediction of separate collection of packaging waste yields and that there are nine important drivers that all together explain roughly 92% (R2=0.918) of the variability in the separate collection yields data.pt_PT
dc.description.sponsorshipLIFE15 ENV/PT/000609
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1007/s12649-019-00656-3pt_PT
dc.identifier.eissn1877-265X
dc.identifier.issn1877-2641
dc.identifier.slugcv-prod-538313
dc.identifier.urihttp://hdl.handle.net/10400.2/9440
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.relationRAW - Recovering nutrients from wastes: eco-innovative solutions to transform waste into resources
dc.subjectHousehold packaging wastept_PT
dc.subjectRegressionpt_PT
dc.subjectSeparate collectionpt_PT
dc.subjectSVMpt_PT
dc.subjectPredictive modelpt_PT
dc.titlePrediction performance of separate collection of packaging waste yields using support vector machinespt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleRAW - Recovering nutrients from wastes: eco-innovative solutions to transform waste into resources
oaire.awardURIinfo:eu-repo/grantAgreement/FCT//SFRH%2FBPD%2F100717%2F2014/PT
oaire.citation.titleWaste and Biomass Valorizationpt_PT
person.familyNameCosta Oliveira
person.familyNameFerreira
person.givenNameVerónica
person.givenNameCélia
person.identifier.ciencia-id6318-20F3-86AF
person.identifier.ciencia-id931E-FBDE-2098
person.identifier.orcid0000-0001-6012-920X
person.identifier.orcid0000-0002-7456-2538
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.cv.cienciaid931E-FBDE-2098 | Célia Maria Dias Ferreira
rcaap.rightsrestrictedAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication424b7c16-b769-4618-8c1c-58b29b36e81a
relation.isAuthorOfPublicatione30010dd-0512-4da6-a0c9-910b47f18b4f
relation.isAuthorOfPublication.latestForDiscoverye30010dd-0512-4da6-a0c9-910b47f18b4f
relation.isProjectOfPublicationbfc45dda-8ea4-41eb-a77f-052f571a7454
relation.isProjectOfPublication.latestForDiscoverybfc45dda-8ea4-41eb-a77f-052f571a7454

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2019_WAVE-Sousa_et_al-SVM-Article_PredictionPerformanceOfSeparat-final.pdf
Size:
818.78 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.97 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Ambiente e Sustentabilidade | Artigos em revistas internacionais / Papers in international journals