The use of synthetic input sequences in time series modeling |
| |
Authors: | Dair José de Oliveira Murilo ED Gomes |
| |
Institution: | a Programa de Pós-Graduação em Engenharia Elétrica, Universidade Federal de Minas Gerais, Av. Antonio Carlos 6627, 31.270-901 Belo Horizonte, MG, Brazil b CORIA/CNRS UMR 6614, Université et INSA de Rouen, Av. de l'Université, BP 12, F-76801 Saint-Etienne du Rouvray cedex, France |
| |
Abstract: | In many situations time series models obtained from noise-like data settle to trivial solutions under iteration. This Letter proposes a way of producing a synthetic (dummy) input, that is included to prevent the model from settling down to a trivial solution, while maintaining features of the original signal. Simulated benchmark models and a real time series of RR intervals from an ECG are used to illustrate the procedure. |
| |
Keywords: | Nonlinear modeling Nonlinear time-series analysis |
本文献已被 ScienceDirect 等数据库收录! |
|