Combining boosted trees with metafeature engineering for predictive maintenance

Vítor Cerqueira*, Fábio Pinto, Claudio Sá, Carlos Soares

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

11 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationAdvances in Intelligent Data Analysis
Subtitle of host publication15th International Symposium, IDA 2016, Stockholm, Sweden, October 13-15, 2016, Proceedings
EditorsHenrik Boström, Panagiotis Papapetrou, Arno Knobbe, Carlos Soares
Place of PublicationCham
Number of pages5
ISBN (Electronic)978-3-319-46349-0
ISBN (Print)978-3-319-46348-3
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event15th International Symposium on Intelligent Data Analysis, IDA 2016 - Stockholm, Sweden
Duration: 13 Oct 201615 Oct 2016
Conference number: 15

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameInformation Systems and Applications, incl. Internet/Web, and HCI


Conference15th International Symposium on Intelligent Data Analysis, IDA 2016
Abbreviated titleIDA 2016
Internet address


  • Anomaly detection
  • Boosting
  • Metalearning
  • Predictive maintenance


Dive into the research topics of 'Combining boosted trees with metafeature engineering for predictive maintenance'. Together they form a unique fingerprint.

Cite this