A genetic algorithms based technique for computing the nonlinear least squares estimates of the parameters of sum of exponentials model
A genetic algorithms based technique for computing the nonlinear least squares estimates of the parameters of sum of exponentials model
复制标题
DOI：
10.1016/j.eswa.2011.12.033
复制
发表时间：
2012-06-01
影响因子：
8.5
通讯作者：
Mitra, Amit
中科院分区：
文献类型：
--
作者：
Mitra, Sharmishtha;Mitra, Amit
非线性指数和模型的参数估计是时间序列分析中的一个重要问题。指数和模型可应用于对各种各样的真实的生活应用中的各种物理现象进行建模。非线性最小二乘估计的求解是一个非常困难的问题.在本文中，我们提出了一个精英世代遗传算法的迭代过程中计算非线性最小二乘估计。仿真研究和真实的寿命数据拟合的例子表明，所提出的技术令人满意的性能。(C)2011爱思唯尔有限公司保留所有权利。
Estimation of the parameters of a nonlinear sum of exponentials model is an important and well studied problem in time series analysis. The sum of exponentials model finds application in modeling various physical phenomena in a wide variety of real life applications. The problem of finding the nonlinear least squares estimates in well known to be numerically difficult. In this paper, we propose an elitist generational genetic algorithm based iterative procedure for computing the nonlinear least squares estimates. Simulation studies and real life data fitting examples indicate satisfactory performance of the proposed technique. (C) 2011 Elsevier Ltd. All rights reserved.