Combining Boosted Trees with Metafeature Engineering for Predictive Maintenance

dc.contributor.author Vítor Manuel Cerqueira en
dc.contributor.author Fábio Hernâni Pinto en
dc.contributor.author Cláudio Rebelo Sá en
dc.contributor.author Carlos Manuel Soares en
dc.date.accessioned 2017-12-20T11:33:03Z
dc.date.available 2017-12-20T11:33:03Z
dc.date.issued 2016 en
dc.description.abstract We describe a data mining workflow for predictive maintenance of the Air Pressure System in heavy trucks. Our approach is composed by four steps: (i) a filter that excludes a subset of features and examples based on the number of missing values (ii) a metafeatures engineering procedure used to create a meta-level features set with the goal of increasing the information on the original data; (iii) a biased sampling method to deal with the class imbalance problem; and (iv) boosted trees to learn the target concept. Results show that the metafeatures engineering and the biased sampling method are critical for improving the performance of the classifier. en
dc.identifier.uri http://repositorio.inesctec.pt/handle/123456789/4388
dc.identifier.uri http://dx.doi.org/10.1007/978-3-319-46349-0_35 en
dc.language eng en
dc.relation 6211 en
dc.relation 5832 en
dc.relation 5001 en
dc.relation 5527 en
dc.rights info:eu-repo/semantics/openAccess en
dc.title Combining Boosted Trees with Metafeature Engineering for Predictive Maintenance en
dc.type conferenceObject en
dc.type Publication en
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
P-00K-WFP.pdf
Size:
347.68 KB
Format:
Adobe Portable Document Format
Description: