Abstract | ||
---|---|---|
This paper proposes a regime-switching recurrent network model (RS-RNN) for non-stationary time series. The RS-RNN model emits a mixture density with dynamic nonlinear regimes that fit flexibly data distributions with non-Gaussian shapes. The key novelties are: development of an original representation of the means of the component distributions by dynamic nonlinear recurrent networks, and derivation of a corresponding expectation maximization (EM) training algorithm for finding the model parameters. The results show that the RS-RNN applied to a real-world wind speed time series achieves standardized residuals similar to popular previous models, but it is more accurate distribution forecasting than other linear switching (MS-AR) and nonlinear neural network (MLP and RNN) models. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.asoc.2019.04.009 | Applied Soft Computing |
Field | DocType | Volume |
Mixture distribution,Mathematical optimization,Nonlinear system,Wind speed,Studentized residual,Expectation–maximization algorithm,Recurrent neural network,Algorithm,Artificial neural network,Mathematics,Network model | Journal | 80 |
ISSN | Citations | PageRank |
1568-4946 | 1 | 0.35 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nikolay Y. Nikolaev | 1 | 57 | 6.46 |
Evgueni N. Smirnov | 2 | 24 | 20.38 |
Daniel Stamate | 3 | 66 | 36.68 |
Robert Zimmer | 4 | 21 | 4.59 |