• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Artikel
  4. Benchmarking of Data Preprocessing Methods for Machine Learning-Applications in Production
 
  • Details
  • Full
Options
2021
Journal Article
Titel

Benchmarking of Data Preprocessing Methods for Machine Learning-Applications in Production

Abstract
The application of machine learning (ML) is becoming increasingly common in production. However, many ML-projects in production fail due to poor data quality. To increase the quality, data needs to be preprocessed. Hundreds of methods exist for data preprocessing (DPP) that are selected manually depending on use-case requirements. For these reasons, DPP is currently performed unstructured and accounts for 80 % of ML-projects duration. Thus, we introduce a structured DPP-approach, in which DPP-methods are recommended based on production use-case requirements by benchmarking identified DPP-methods according to ML-model performance on five data sets. The approach is validated through two new use-cases.
Author(s)
Frye, Maik
Fraunhofer-Institut für Produktionstechnologie IPT
Mohren, Johannes
Fraunhofer-Institut für Produktionstechnologie IPT
Schmitt, Robert H.
Fraunhofer-Institut für Produktionstechnologie IPT
Zeitschrift
Procedia CIRP
Project(s)
EPIC
Funder
European Commission EC
Konferenz
Conference on Manufacturing Systems (CMS) 2021
Thumbnail Image
DOI
10.1016/j.procir.2021.11.009
Externer Link
Externer Link
Language
English
google-scholar
Fraunhofer-Institut für Produktionstechnologie IPT
Tags
  • data preprocessing

  • data preparation

  • machine learning

  • artificial intelligen...

  • production

  • manufacturing

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022