Feature selection and bleach time modelling of paper pulp using tree based learners
2016 (English)In: WISE 2016 / [ed] Springer International Publishing, China - Shanghai, 2016, 385-396 p.Conference paper (Refereed)
Paper manufacturing is energy demanding and improvedmodelling of the pulp bleach process is the main non-invasive means ofreducing energy costs. In this paper, time it takes to bleach paper pulpto desired brightness is examined. The model currently used is analysedand benchmarked against two machine learning models (Random Forestand TreeBoost). Results suggests that the current model can be super-seded by the machine learning models and it does not use the optimalcompact subset of features. Despite the differences between the machinelearning models, a feature ranking correlation has been observed for thenew models. One novel, yet unused, feature that both machine learningmodels found to be important is the concentration of bleach agent.
Place, publisher, year, edition, pages
China - Shanghai, 2016. 385-396 p.
Computer Notes in Computer Science, ISSN 0302-9743 ; 10042
Feature selection, Machine learning, CFS, Random forest, TreeBoost, XGBoost, Paper manufacturing
Research subject Complex Systems – Microdata Analysis
IdentifiersURN: urn:nbn:se:du-23410DOI: 10.1007/978-3-319-48743-4_31ISBN: 978-3-319-48742-7ISBN: 978-3-319-48743-4OAI: oai:DiVA.org:du-23410DiVA: diva2:1047928
Quat 2016 (4th Annual Workshop on Data Quality and Trust in Big Data), Shanghai, November 7-10 2016