Reconstructing Improper Values with Linear RegressionΒΆ

Non-Causal Step

This step first estimates the parameters of the linear model using the data. Then, the linear model with known parameters can reconstruct improper values at corresponding times.

Input Parameters

  1. Input data including improper values
  2. Definition of improper values (‘nan’, ‘inf’, or ‘null’, etc.)

Output Parameters

  1. Output data excluding improper values




Linear Regression


  • J. Han, M. Kamber and J. Pei, Data Mining - Concepts and Techniques, 3rd ed., Amsterdam: Morgan Kaufmann Publishers, 2012.