Adaptive iteratively reweighted penalized least squares [1]
This function calls ml-airpls
References: [1] Zhang, Z.-M.; Chen, S.; Liang, Y.-Z. Baseline Correction Using Adaptive Iteratively Reweighted Penalized Least Squares. Analyst 2010, 135 (5), 1138–1146. https://doi.org/10.1039/B922045C.
(object?
= {}
)
Options object
Name | Description |
---|---|
options.x Array<number>?
|
Optional, Independent axis variable. If not specified, we use a linear grid |
options.regression object?
|
Options for the regression |
options.regression.maxIterations number
(default 100 )
|
Maximum number of allowed iterations |
options.regression.regressionOptions any?
|
Options for regressionFunction |
options.regression.tolerance number
(default 0.001 )
|
Convergence error tolerance |
(any)
§Regression = PolynomialRegression] - Regression class with a predict method
BaselineOutput
:
Type: Object
Iterative polynomial fitting [1]
Implementation based on ml-baseline-correction-regression
References: [1] Gan, F.; Ruan, G.; Mo, J. Baseline Correction by Improved Iterative Polynomial Fitting with Automatic Threshold. Chemometrics and Intelligent Laboratory Systems 2006, 82 (1), 59–65. https://doi.org/10.1016/j.chemolab.2005.08.009.
(object?
= {}
)
Options object
Name | Description |
---|---|
options.x Array<number>?
|
Optional, Independent axis variable. If not specified, we use a linear grid |
options.regression Object?
|
|
options.regression.maxIterations number
(default 100 )
|
Maximum number of allowed iterations |
options.regression.Regression function
(default PolynomialRegression )
|
Regression class with a predict method |
options.regression.regressionOptions Object?
|
Options for regressionFunction |
options.regression.tolerance number
(default 0.001 )
|
Convergence error tolerance |
options.regression Object?
|
BaselineOutput
:
BaselineOutput
:
Rolling ball baseline correction algorithm. From the abstract of (1): "This algorithm behaves equivalently to traditional polynomial backgrounds in simple spectra, [...] and is considerably more robust for multiple overlapping peaks, rapidly varying background [...]
The baseline is the trace one gets by rolling a ball below a spectrum. Algorithm has three steps: Finding the minima in each window, find maxima among minima and then smooth over them by averaging.
Algorithm described in (1), but in the implementation here the window width does not change.
Reference: (1) Kneen, M. A.; Annegarn, H. J. Algorithm for Fitting XRF, SEM and PIXE X-Ray Spectra Backgrounds. Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms 1996, 109–110, 209–213. https://doi.org/10.1016/0168-583X(95)00908-6. (2) Kristian Hovde Liland, Bjørn-Helge Mevik, Roberto Canteri: baseline. https://cran.r-project.org/web/packages/baseline/index.html
BaselineOutput
:
BaselineOutput
: