Baseline Correction Based on a Search Algorithm from Artificial Intelligence
Authors:
- 6 January 2021
- journal article
- research article
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 75 (5) , 531-544
Abstract
Many spectra have a polynomial-like baseline. Iterative polynomial fitting is one of the most popular methods for baseline correction of these spectra. However, the baseline estimated by iterative polynomial fitting may have a substantial error when the spectrum contains significantly strong peaks or have strong peaks located at the endpoints. First, iterative polynomial fitting uses temporary baseline estimated from the current spectrum to identify peak data points. If the current spectrum contains strong peaks, then the temporary baseline substantially deviates from the true baseline. Some good baseline data points of the spectrum might be mistakenly identified as peak data points and are artificially re-assigned with a low value. Second, if a strong peak is located at the endpoint of the spectrum, then the endpoint region of the estimated baseline might have a significant error due to overfitting. This study proposes a search algorithm-based baseline correction method (SA) that aims to compress sample the raw spectrum to a dataset with small number of data points and then convert the peak removal process into solving a search problem in artificial intelligence to minimize an objective function by deleting peak data points. First, the raw spectrum is smoothened out by the moving average method to reduce noise and then divided into dozens of unequally spaced sections on the basis of Chebyshev nodes. Finally, the minimal points of each section are collected to form a dataset for peak removal through search algorithm. SA selects the mean absolute error as the objective function because of its sensitivity to overfitting and rapid calculation. The baseline correction performance of SA is compared with those of three baseline correction methods, the Lieber and Mahadevan-Jansen method, adaptive iteratively reweighted penalized least squares method, and improved asymmetric least squares method. Simulated and real Fourier transform infrared and Raman spectra with polynomial-like baselines are employed in the experiments. Results show that for these spectra the baseline estimated by SA has fewer error than those by the three other methods.Keywords
Funding Information
- Science and Technology Plan General Program of Beijing Municipal Commission of Education (KM201710005009)
- National Natural Science Foundation of China (51706005)
This publication has 27 references indexed in Scilit:
- A Raman peak recognition method based automated fluorescence subtraction algorithm for retrieval of Raman spectra of highly fluorescent samplesAnalytical Methods, 2015
- Range‐independent background subtraction algorithm for recovery of Raman spectra of biological tissueJournal of Raman Spectroscopy, 2012
- Automated Autofluorescence Background Subtraction Algorithm for Biomedical Raman SpectroscopyApplied Spectroscopy, 2007
- Baseline correction by improved iterative polynomial fitting with automatic thresholdChemometrics and Intelligent Laboratory Systems, 2006
- Investigation of Selected Baseline Removal Techniques as Candidates for Automated ImplementationApplied Spectroscopy, 2005
- Automated Method for Subtraction of Fluorescence from Biological Raman SpectraApplied Spectroscopy, 2003
- Wavelet estimation of a base-line signal from repeated noisy measurements by vertical block shrinkageComputational Statistics & Data Analysis, 2002
- Optimum zero-area filter for nuclear signal sequencesNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1997
- Background subtraction from transition metal 2p XPS by deconvolution using ligand atom XPS: study on first transition metal cyanide complexesJournal of Electron Spectroscopy and Related Phenomena, 1997
- A New Baseline Correction Algorithm Using Objective CriteriaApplied Spectroscopy, 1987