Skip to contents

Correlation Optimized Warping Alignment

Source: R/align.R
step_measure_align_cow.Rd

step_measure_align_cow() creates a specification of a recipe step that aligns spectra using Correlation Optimized Warping (COW). This method uses piecewise linear warping to correct for non-linear shifts.

Usage

step_measure_align_cow(
  recipe,
  measures = NULL,
  reference = c("mean", "median", "first"),
  segment_length = 30L,
  slack = 1L,
  role = NA,
  trained = FALSE,
  skip = FALSE,
  id = recipes::rand_id("measure_align_cow")
)

Arguments

recipe

A recipe object.

measures

An optional character vector of measure column names.

reference

How to determine the reference: "mean" (default, mean spectrum from training), "median" (median spectrum from training), or "first" (first sample).

segment_length

Length of each segment for warping. Default is 30. Tunable via align_segment_length().

slack

Maximum compression/expansion per segment in points. Default is 1. A slack of 1 means each segment can shrink or expand by 1 point.

role

Not used.

trained

Logical indicating if the step has been trained.

skip

Logical. Should the step be skipped when baking?

id

Unique step identifier.

Value

An updated recipe with the new step added.

Details

Correlation Optimized Warping (COW) divides signals into segments and uses dynamic programming to find the optimal piecewise linear warping that maximizes correlation with the reference spectrum.

Key parameters:

  • segment_length: Controls the resolution of warping. Smaller segments allow more local corrections but increase computation.

  • slack: Controls how much each segment can stretch or compress. Larger values allow more flexibility but may introduce artifacts.

This is a pure R implementation based on Nielsen et al. (1998).

References

Nielsen, N.P.V., Carstensen, J.M., and Smedsgaard, J. (1998). Aligning of single and multiple wavelength chromatographic profiles for chemometric data analysis using correlation optimised warping. Journal of Chromatography A, 805, 17-35.

See also

Other measure-align: step_measure_align_dtw(), step_measure_align_ptw(), step_measure_align_reference(), step_measure_align_shift()

Examples

library(recipes)

rec <- recipe(water + fat + protein ~ ., data = meats_long) |>
  update_role(id, new_role = "id") |>
  step_measure_input_long(transmittance, location = vars(channel)) |>
  step_measure_align_cow(segment_length = 20, slack = 2) |>
  prep()

bake(rec, new_data = NULL)
#> # A tibble: 215 × 5
#>       id water   fat protein .measures
#>    <int> <dbl> <dbl>   <dbl>    <meas>
#>  1     1  60.5  22.5    16.7 [100 × 2]
#>  2     2  46    40.1    13.5 [100 × 2]
#>  3     3  71     8.4    20.5 [100 × 2]
#>  4     4  72.8   5.9    20.7 [100 × 2]
#>  5     5  58.3  25.5    15.5 [100 × 2]
#>  6     6  44    42.7    13.7 [100 × 2]
#>  7     7  44    42.7    13.7 [100 × 2]
#>  8     8  69.3  10.6    19.3 [100 × 2]
#>  9     9  61.4  19.9    17.7 [100 × 2]
#> 10    10  61.4  19.9    17.7 [100 × 2]
#> # ℹ 205 more rows