论文信息 - Extraction of signal by a time series model and screening out micro earthquakes

Extraction of signal by a time series model and screening out micro earthquakes

Abstract A model for the decomposition of time series into several components is shown. In the model each component is expressed by an autoregressive model. The minimum AIC procedure for the estimation of these models is shown. The crucial problem of estimating changing variance of the model was solved by the techniques of piecewise modeling and local modeling. The extraction of micro earthquake signal was shown to exemplify the proposed procedures. The stability of the procedure and a possible simplication of the procedure were also considered by using the same data set.

Genshiro Kitagawa | Tetsuo Takanami | G. Kitagawa | T. Takanami

[1] G. Kitagawa,et al. A Smoothness Priors–State Space Modeling of Time Series with Trend and Seasonality , 1984 .

[2] Genshiro Kitagawa,et al. A procedure for the modeling of non-stationary time series , 1978 .

[3] G. Kitagawa,et al. A smoothness priors time-varying AR coefficient modeling of nonstationary covariance time series , 1985, IEEE Transactions on Automatic Control.

[4] H. Akaike,et al. Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[5] Genshiro Kitagawa,et al. An approach to the prediction of time series with trends and seasonalities , 1982, 1982 21st IEEE Conference on Decision and Control.

[6] Hirotugu Akaike,et al. Likelihood and the Bayes procedure , 1980 .

[7] G. Kitagawa. Changing spectrum estimation , 1983 .

[8] Genshiro Kitagawa,et al. A NONSTATIONARY TIME SERIES MODEL AND ITS FITTING BY A RECURSIVE FILTER , 1981 .