Parameter estimation in exponential models by linear and nonlinear fitting methods

Abstract

Estimation of unknown parameters in exponential models by linear and nonlinear fitting methods is discussed. Based on the extreme value theorem and Taylor series expansion, it is proved theoretically that the parameters estimated by the linear fitting method alone cannot minimize the sum of the squared residual errors in the measurement data when measurement noise is involved in the data. Numerical simulation is performed to compare the performance of the linear and nonlinear fitting methods. Simulation results show that the linear method can obtain only a suboptimal estimate of the unknown parameters and that the nonlinear method gives more accurate results. Application of the fitting methods is demonstrated where the water spectral attenuation coefficient is estimated from underwater images and imaging distances, which supports the improvement in the accuracy of parameter estimation by the nonlinear fitting method.

Keywords

Exponential model / Parameter estimation / Linear least squares / Nonlinear fitting

References

[1] Adi, N.S., 2015. Characterisation of the light environment and biophysical parameters of seagrass using remote sensing. PhD Thesis, The University of Queensland, Brisbane, Australia, p.23–38. http://dx.doi.org/10.14264/uql.2015.998

[2] Åhlén, J., Bengtsson, E., Sundgren, D., 2006. Evaluation of underwater spectral data for color correction applications. Proc. 5th WSEAS Int. Conf. on Circuits, Systems, Electronics, Control & Signal Processing, p.321–326.

[3] Bardaji, R., Sánchez, A.M., Simon, C., et al, 2016. Estimating the underwater diffuse attenuation coefficient with a low-cost instrument: the KdUINO DIY buoy. Sensors, 16(3):373–387. http://dx.doi.org/10.3390/s16030373

[4] Floudas, C.A., Pardalos, P.M., 2001. Encyclopedia of Optimization. Kluwer Academic Publishers, Norwell, p.1129–1134. http://dx.doi.org/10.1007/0-306-48332-7

[5] Guo, Y.L., Song, H., Liu, H.B., et al, 2016. Model-based restoration of underwater spectral images captured with narrowband filters. Opt. Expr., 24(12):13101–13120. http://dx.doi.org/10.1364/OE.24.013101

[6] Hartley, H.O., 1961. The modified Gauss-Newton method for the fitting of nonlinear regression functions by least squares. Technometrics, 3(2):269–280. http://dx.doi.org/10.2307/1266117

[7] He, Q.R., Li, L.P., 2015. Algorithm study on reducing frequency measurement variance of acousto-optic spectrum analyzer. Infrar. Laser Eng., 44(5):1564–1568 (in Chinese).

[8] Kaeli, J.W., Singh, H., Murphy, C., et al, 2011. Improving color correction for underwater image surveys. Proc. IEEE/MTS Oceans, p.805–810.

[9] Lai, J.S., Yang, B., Lin, D.M., et al, 2013. The allometry of coarse root biomass: log-transformed linear regression or nonlinear regression. PLoS One, 8(10):e77007. http://dx.doi.org/10.1371/journal.pone.0077007

[10] Levenberg, K., 1944. A method for the solution of certain non-linear problems in least squares. Q. Appl. Math., 2:164–168. http://dx.doi.org/10.1090/qam/10666

[11] Lieb, S.G., 1997. Simplex method of nonlinear least-squares: a logical complementary method to linear least-square analysis of data. J. Chem. Educat., 74(8):1008–1011. http://dx.doi.org/10.1021/ed074p1008

[12] Liu, C.Q., Ma, J.S., Shao, X.L., et al, 2013. Detection of Gaussian beam distribution of light intensity. Opt. Instrum., 35(6):69–73 (in Chinese). http://dx.doi.org/10.3969/j.issn.1005-5630.2013.06.014

[13] Marquardt, D.W., 1963. An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Ind. Appl. Math., 11(2):431–441. http://dx.doi.org/10.1137/0111030

[14] Mascaro, J., Litton, C.M., Hughes, R.F., et al, 2011. Minimizing bias in biomass allometry: model selection and log-transformation of data. Biotropica, 43(6):649–653. http://dx.doi.org/10.1111/j.1744-7429.2011.00798.x

[15] Novković, D., Nadderd, L., Kandić, A., et al, 2006. Testing the exponential decay law of gold 198Au. Nucl. Instrum. Methods Phys. Res. Sect. A, 566(2):477–480. http://dx.doi.org/10.1016/j.nima.2006.07.044

[16] Peterson, P., Baker, E., McGaw, B., 2010. International Encyclopedia of Education. Elsevier Science, Oxford, p.339–346.

[17] Schechner, Y.Y., Karpel, N., 2004. Clear underwater vision. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.536–543. http://dx.doi.org/10.1109/CVPR.2004.1315078

[18] Semkow, T.M., 2007. Exponential decay law and nuclear statistics. In: Semkow, T.M., Pommé, S., Jerome, S., et al (Eds.), Applied Modeling and Computations in Nuclear Science. ACS, Washington DC. http://dx.doi.org/10.1021/bk-2007-0945.ch004

[19] Simon, A., Shanmugam, P., 2016. Estimation of the spectral diffuse attenuation coefficient of downwelling irradiance in inland and coastal waters from hyperspectral remote sensing data: validation with experimental data. Int. J. Appl. Earth Observ. Geoinform., 49:117–125. http://dx.doi.org/10.1016/j.jag.2016.02.003

[20] Swinehart, D.F., 1962. The Beer-Lambert law. J. Chem. Educat., 39(7):333–335. http://dx.doi.org/10.1021/ed039p333

[21] Vickery, P.J., 2005. Simple empirical models for estimating the increase in the central pressure of tropical cyclones after landfall along the coastline of the United States. J. Appl. Meteorol., 44:1807–1826. http://dx.doi.org/10.1175/JAM2310.1

[22] Wei, J.W., Lee, Z.P., 2013. Model of the attenuation coefficient of daily photosynthetically available radiation in the upper ocean. Methods Oceanogr., 8:56–74. http://dx.doi.org/10.1016/j.mio.2013.12.001

[23] Xiao, X., White, E.P., Hooten, M.B., et al, 2011. On the use of log-transformation vs. nonlinear regression for analyzing biological power laws. Ecology, 92(10):1887–1894. http://dx.doi.org/10.1890/11-0538.1

RIGHTS & PERMISSIONS

2017 Zhejiang University and Springer-Verlag Berlin Heidelberg