We propose a simple differential method and a refined Roonizi’s method to fit single Gaussian function and integro-differential method to fit two Gaussian functions. The conventional method for fitting Gaussian functions is an iterative procedure. The proposed methods, being linear in estimated parameters, alleviate the problem of critical initial guess needed in iterative procedures. The experimental results confirm the methods perform better or in a competitive manner compared to Caruana’s, Guo’s, Roonizi’s and FAS algorithm for single Gaussian case. It is found that the proposed integro-differential method to fit two Gaussian functions is stable and identifies Gaussian parameters in an efficient way.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Al-Nahhal I, Dobre OA, Basar E, Moloney C, Ikki S (2019) A fast, accurate, and separable method for fitting a gaussian function [tips tricks]. IEEE Signal Process Mag 36(6):157–163. https://doi.org/10.1109/MSP.2019.2927685
Bobroff N (1986) Position measurement with a resolution and noise-limited instrument. Rev Scientific Instrum 57(6):1152–1157. https://doi.org/10.1063/1.1138619
Caruana RA, Searle RB, Heller T, Shupack SI (1986) Fast algorithm for the resolution of spectra. Anal Chem 58(6):1162–1167. https://doi.org/10.1021/ac00297a041
Guo H (2011) A simple algorithm for fitting a gaussian function [dsp tips and tricks]. IEEE Signal Process Mag 28(5):134–137. https://doi.org/10.1109/MSP.2011.941846
Ireland J (2005) Precision limits to emission-line profile measuring experiments. Astrophys J 620(2):1132–1139. https://doi.org/10.1086/427230
Kheirati Roonizi E (2013) A new algorithm for fitting a gaussian function riding on the polynomial background. IEEE Signal Process Lett 20(11):1062–1065. https://doi.org/10.1109/LSP.2013.2280577
Lenz DD, Ayres TR (1992) Errors associated with fitting gaussian profiles to noisy emission-line spectra. Publ Astron Soc Pac 104:1104. https://doi.org/10.1086/133096
Oppenheim AV, Wilsky AS, Young I (1983) Signals and systems. Prentice-Hall, New Jersey
Tang Q, Chen Z, Ward R, Elgendi M (2020) Synthetic photoplethysmogram generation using two gaussian functions. Scientific Reports 10(1):13883. https://doi.org/10.1038/s41598-020-69076-x
Winick KA (1986) Cramér-rao lower bounds on the performance of charge-coupled-device optical position estimators. J Opt Soc Am A 3(11):1809–1815. https://doi.org/10.1364/JOSAA.3.001809
The authors are expressing their sincere gratitude to the anonymous reviewers for their comments. This research was funded by NRF with 2017R1E1A1A03070061.
About this article
Cite this article
Kwak, M., Lkhagvasuren, B. & Sun, X. An Efficient Method for Fitting Gaussian Functions. Iran J Sci Technol Trans Sci (2021). https://doi.org/10.1007/s40995-021-01079-3
- Gaussian functions
- Nonlinear fitting
- Parameter estimation