A normalization method for contextual data: Experience from a large-scale application

  • Sylvain Létourneaue
  • Stan Matwin
  • Fazel Familie
Regular Papers Applications of ML
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1398)


This paper describes a pre-processing technique to normalize contextually-dependent data before applying Machine Learning algorithms. Unlike many previous methods, our approach to normalization does not assume that the learning task is a classification task. We propose a data pre-processing algorithm which modifies the relevant attributes so that the effects of the contextual attributes on the relevant attributes are cancelled. These effects are modeled using a novel approach, based on the analysis of variance of the contextual attributes. The method is applied on a massive data repository in the area of aircraft maintenance.


Learning in contextual domains attribute normalization datamining 


  1. 1.
    Kubat, M., Holte, R. C., Matwin, S.: Machine Learning for the Detection of Oil Spills in Satellite radar Images Machine Learning Journal, Special Issue on Applications of ML. (1998) to appear.Google Scholar
  2. 2.
    Letourneau, S., Matwin, S., Famili, F.: A Normalization Method for Contextual Data: Experience From A Large-Scale Application. TR-98-02,≈stan/public_html/techrep/ Scholar
  3. 3.
    Taylor, C., Nakhaeizadeh, G.: Learning in Dynamically Changing Domains: Theory Revision and Context Dependence Issues. Proceedings of ECML-97. (1997) 353–360.Google Scholar
  4. 4.
    TURNEY, P, Halasz, M: Contextual Normalization Applied to Aircraft Gas Turbine Engine Diagnosis. Journal of Applied Intelligence 3 (1993) 109–129CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Sylvain Létourneaue
    • 1
  • Stan Matwin
    • 2
  • Fazel Familie
    • 1
  1. 1.Integrated Reasoning GroupNational Research Council of CanadaOttawa
  2. 2.School of Information Technology and EngineeringUniversity of OttawaCanada

Personalised recommendations