Abstract
It was found that the LEP data was sometimes contaminated with unexpectedly larger noise mainly due to the geocorona EUV radiation. Its noise level is so high that we are obliged to subtract the background noise in ground processing when we intend to analyze such LEP data. We therefore propose an efficient and useful procedure for eliminating this background noise, which is highly implemented so as to reduce the computing time. This method is based on a Bayesian smoothness prior approach with a state space modeling. The estimated background noise component is easily realized as a fixed-interval smoothed value by using the recursive Kalman filter and smoother algorithm. In addition, since we use an objective criterion ABIC to choose the best model for the LEP data with the background noise, then the background noise component is automatically and objectively (not ad-hoc) subtracted according to the characteristics of noise such as the signal-to-noise ratio, its intensity, and various nonstationarity. A detail description of the whole procedure based on a Bayesian approach can be shown.
