Gradient-based Parameter Estimation for a Nonlinear Exponential Autoregressive Time-series Model by Using the Multi-innovation Jian Pan*, Yuqing Liu, and Jun Shu
International Journal of Control, Automation, and Systems, vol. 21, no. 1, pp.140-150, 2023
Abstract : The parameter estimation methods for the nonlinear exponential autoregressive model are investigated in this paper. We develop a forgetting factor gradient parameter estimation algorithm for improving the estimation accuracy. For the purpose of improving the identification accuracy further, a forgetting factor multi-innovation stochastic gradient algorithm is derived by using the multi-innovation theory. The effectiveness of the proposed algorithms is proved by a simulation example.
Keyword :
Exponential autoregressive model, forgetting factor, gradient search, multi-innovation theory, parameter estimation.
|