18.1.1 The Smooth Dialog Box


Smooth smooth.png
  • Menu Command: Analysis: Signal Processing: Smooth
  • Window Types: Workbook, Graph
  • X-Function Script and GUI Examples: smooth
Dialog Theme See Dialog Themes.
Recalculate

See Recalculating Analysis Results.

Input

Specifies the input XY data range to be smoothed.
Note: From Origin 2024, it supports to smooth multiple datasets in the same Worksheet at one processing, for example XYYY and XYXYXY data columns.

See Specifying Your Input Data.

Method

Specifies the smoothing method to be used. The default is Savitzky-Golay.

  • Adjacent-Averaging: This method essentially takes the average of a certain number (which you specify) of data points around each point in your data and replaces that point with the new average value.
  • Savitzky-Golay: This method is actually performing a local polynomial regression. It is best suited to remove noise without affecting the overall signal shape. Original data values are replaced with fitted values.
  • Percentile Filter: This method is also known as rank-order filter. It essentially finds the specified percentile of data points in the data window around each point in your data and replaces that point with the percentile. It is best suited for removing shot noise.
  • FFT Filter: This method is based on FFT low-pass filter. It should be used when the frequency of noise is higher than the true signal. In essence, it removes the high-frequency components with a parabolic window. Frequencies not less than the cutoff frequency will be discarded.
  • LOWESS and LOESS: The name Lowess and Loess is the abbreviation for "locally weighted scatter plot smoothing". It is best used when there are a large number of data points. Please refer to its algorithm for details.
  • Binomial: Binomial filter is a weighted moving average filters whose weight is derived from binomial coefficients. It is a low-pass filters for filtering out high frequency noise.
Weighted Average

When Method is Adjacent-Averaging, check this box to use weighted averaging.

Specify Span by

When Method is either Lowess or Loess, you can specify span by these three options:

  • Points of Window: Use point of windows for span
  • Proportion: Use the proportion (0-1) for span
  • X Value: Use the specified X value for span
Points of Window

When Points of Window is selected for Specify Span by, specifies the number of points in the moving window. Otherwise, you can use this parameter to control the cutoff frequency for the FFT filter. Larger values produce greater smoothing. Must be a non-zero positive value. See the algorithm section for the computation of cutoff frequency.

Span (0-1)

When Proportion is selected for Specify Span by, controls the proportion value for the span. Larger values produce greater smoothing.

X Value

When X Value is selected for Specify Span by, specifies the X Value. By default, this X Value is 0.1*(x max-x min).

Boundary Condition

Not available when Method is FFT Filter/Lowess/Loess.

  • None: No padding is performed.
  • Reflect: Pads data by reflecting signal at both ends.
  • Repeat: Pads data by repeating the ending point at both ends.
  • Periodic: Treats data as a periodic signal.
  • Extrapolate: Uses linear extrapolation to pad signal at both ends.
Polynomial Order

Available when Method is Savitzky-Golay.

Percentile

Controls the percentile to be used in percentile filtering. The default is 50%, which corresponds to replacing the signal point with median value of the data points in the data window. Available only when Method is Percentile Filter.

Cutoff Frequency

Read-only box showing the cutoff frequency of the low-pass filter. This parameter is visible only when Method is FFT Filter or Binomial.

Sampling Interval

Sampling interval. Clear Auto checkbox to set Sample Interval manually. Only available when Method is Binomial.

Order

Default value is 1. Clear the Auto checkbox to set Order manually. Only available when Method is Binomial.

Output

Determine where to output the smoothed signal. See Output Results.