Scaler

The Scaler module can be used to perform feature scaling.

Depending on the operation mode, the scaling parameters are used in different ways.

Normalization

Standardization:

The scaling parameters can be configured directly. Alternatively, they can be imported from a file.

Optionally, a Boolean signal can be selected for the Enable Execution input so that the algorithm is only active if the value of the selected signal is TRUE.

Configuration options

• Scaling Mode: Mode for scaling.
  Normalization: Result has a value range of 0..+1
  Standardization: Result has a value range of -1..+1
• Scaling Param 1: The value of the first scaling parameter depends on the scaling mode set.
  Normalization: Highest value of the input signal
  Standardization: Mean value of the input signal
• Scaling Param 2: The value of the second scaling parameter depends on the scaling mode set.
  Normalization: Smallest value of the input signal
  Standardization: Standard deviation of the input signal
• File Path (optional): File path to a file with previously determined parameters. The file is created by the Scaler Fitting module. File type: json.

Output values

• Result: Outputs the calculated value. This is calculated from the two scaling parameters depending on the scaling mode.
  Normalization: Result has a value range of 0..+1
  Standardization: Result has a value range of -1..+1