NONLINEAR REGRESSION PARAMETER ESTIMATES USING GENETIC ALGORITHMS
Keywords:
Local optimal, Optimal estimates, Levenberg – Marquadt, Gauss NewtonAbstract
Deterministic algorithm such as Gauss Newton and Levenberg - Marquadt are still well established practice for obtaining optimal estimates in nonlinear regression. These methods however, have certain pitfalls of multiple local optimal, non-invertibility, differentiability that results to misleading estimates. Under these circumstances, this study is aimed at using optimization techniques in obtaining optimal estimates of complex nonlinear regression model. We investigated the effectiveness and simplicity of particle swarm optimization and genetic algorithm on five (5) test-bed problems obtained from the National Institute of Standards and
Technology (NIST) website. R codes were developed for each model. Each algorithm was tried ten (10) times for each model for at least 100 iterations. The results obtained were displayed on tables and graphs. Particle Swarm Optimization and Genetic Algorithms proved to be efficient, robust and can be considered reliable in obtaining the parameter estimates for Nonlinear Regression Model.
Downloads
References
Seyedmonir S., Bayrami M. Ghoushchi S. J., Yengnjeh A. A. and Herawi H. M. (2021). Extended fully fuzzy linear regression to analyses a solid cantilever beam moment. Hindawi Mathematical problem in enginnering. Vol. 2021. Article ID 2684816.http://doiorg/10.1155/2021/2684816
Kin H. and Jung H. Y, (2020). Ridge fuzzy regression modelling for solving multicollinearity. MDPI. Mathematic 8, 1572 doi: 10.3390/math809157
Zhang Y. Qu H., Wang W., and Zhao J. (2020). A novel fuzzy time series forecasting model based on multiple linear regression and time series clustering. Hindawi mathematical problems in engineering. Vol. 2020, Article ID 9546792. https://doi.org/10.1155/2020/9546792
Rao, U. (2009). Characteristics, Correlates, and Outcomes of childhood and adolescent depressive disorders. https://pubdocs. worldbank.org
Akoa B. E., & Lebowsky, F. (2013). Video decoder monitoring using nonlinear regression. IEEE 19thInternational On-line Testing Symposium (IOLTS), 175-178.
Chandrashaker Reddy B., Venkat Prasad Reddy P., & Rajeshwari M., Kavya Y. Sai (2017). Correlation of GA and PSO for Analysis of Efficient optimization. International Journal of Advance Research and Development. Vol. 2.
Shafi M.A., Rusiman M. S. and Abdullahi S. N. S. (2021) Application of fuzzy linear regression with symmetric parameter for predicting tumor size of colorectal cancer. Mathematics and Statistic (1); 36 -40.
Demidenko, E. (2007). Sample size determination for Logistic Regression. Revisited. https://www.researchgate.net>6649.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 The Journals of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
