DEVICE AND METHOD TO MODEL RANDOM PROCESS BY USING LEAST-SQUARES AUTOREGRESSIVE PARAMETER ESTIMATION WITH REDUCED LENGTH

摘要

The present invention provides a device and a method to model a random process by using least-squares autoregressive parameter estimation with reduced length. The random process modeling device includes: an autocorrelation processor generating or estimating an autocorrelation of length m in regard to a stochastic process; and a least squares estimation (LS estimation) processor connected to the autocorrelation processor. The least squares estimation processor models the stochastic process by estimating a p order autoregressive parameter through least squares regression (LS regression). Here, m is an integer and p is an integer smaller than m.;COPYRIGHT KIPO 2018