FIT THE CUBIC SPLINE

Fits a cubic (or arbitrary-order) smoothing spline to an input curve using a specified number of knots and regions. Supports optional k-fold cross-validation to automatically select the best spline order and knot count, with a lambda penalty controlling knot contribution. Use this worker to smooth or resample noisy time-history or force-displacement curves.

When to use

Classification: process.

Tagged: cross_validation, cubic_spline, curve_smoothing, curve_transform, downsampling, k-fold, knots, lambda.

Inputs

Label ID Type Default Required Description
Curve In curve_in vector   Input curve (x/y vector) to be fitted with a smoothing spline; typically a time-history or force-displacement signal.
Order order scalar 3   Polynomial order of the spline fit (default 3 = cubic); when cross-validation is enabled, this becomes the maximum order evaluated.
Number Of Knots numberof_knots scalar 1   Number of interior knots placed in the spline (default 1); when cross-validation is enabled, this becomes the maximum number of knots evaluated.
Number Of Regions numberof_regions scalar 1   Number of piecewise regions for the spline (default 1); only used when Validation is set to ‘None’.
Validation validation scalar none   Cross-validation strategy for automatic order/knot selection: ‘None’ uses the fixed parameters directly; ‘K-Fold 3/5/10’ performs k-fold CV to find the optimal configuration (default: None).
Lambda lambda scalar 1   Regularisation penalty factor controlling the contribution of each knot (default 1.0); higher values produce smoother fits with fewer effective knots.

Outputs

Label ID Type Description
Cubic Spline Curve curve_cs_output_1 vector Fitted cubic spline curve (x/y vector) evaluated over the same domain as the input, representing the smoothed or resampled result.

Disciplines

  • data.curve.transform
  • data.signal_processing

Runnable example

A runnable example is registered for this worker. Open the example workflow on the d3VIEW canvas: /api/workflow/example?id=curve_cubic_spline


Auto-generated from transformation schema. Worker id: curve_cubic_spline. Schema hash: 1bca1eb6bc0a. Hand-curated docs in workerexamples/ override this page when present.