Sstep.Smooth.Sonar: Sequential Importance Sampling for A Target with Passive...
In ConvFuncTimeSeries/test_t: Nonlinear time series analysis

Description Usage Arguments Value References

This function uses the sequential importance sampling method to deal with a target with passive sonar for smoothing.

1	Sstep.Smooth.Sonar(mm, xxt, xxt1, ww, vv, par)

`mm`	the Monte Carlo sample size `m`.
`xxt`	the sample in the last iteration.
`xxt1`	the sample in the next iteration.
`ww`	`ww*t(ww)` is the state innovation covariance matrix.
`vv`	`vv*t(vv)` is the covariance matrix of the observation noise.
`par`	a list of parameter values. `H` is the state coefficient matrix, and `W*t(W)` is the state innovation covariance matrix.

The function returns a list with the following components:

`xx`	the new sample.
`logww`	the log weights.

s2 <- 20 #second sonar location at (s2,0) q <- c(0.03,0.03) r <- c(0.02,0.02) nobs <- 200 start <- c(10,10,0.01,0.01) H <- c(1,0,1,0,0,1,0,1,0,0,1,0,0,0,0,1) H <- matrix(H,ncol=4,nrow=4,byrow=TRUE) W <- c(0.5*q[1], 0,0, 0.5*q[2],q[1],0,0,q[2]) W <- matrix(W,ncol=2,nrow=4,byrow=TRUE) V <- diag(r) mu0 <- start SS0 <- diag(c(1,1,1,1))*0.01 simu_out <- simPassiveSonar(nobs,q,r,start,seed=20) yy <- simu_out$yy resample.sch <- rep(1,nobs) xdim <- 4;ydim <- 2; mm <- 5000 par <- list(H=H,W=W,V=V,s2=s2) xx.init <- mu0+SS0 out.s5K <- SMC.Smooth(Sstep.Sonar,Sstep.Smooth.Sonar,nobs,yy,mm,par, xx.init,xdim,ydim,resample.sch)

Tsay, R. and Chen, R. (2019). Nonlinear Time Series Analysis. Wiley, New Jersey.

ConvFuncTimeSeries/test_t documentation built on May 29, 2019, 1:39 p.m.