DecomposeR (version 1.0.2)

gzc.departure: departure of instantaneous frequency to generalized zero-crossing

Description

departure of instantaneous frequency to generalized zero-crossing of instantaneous freqeuncy. The departure is calculated as the exponential of the absolute difference of logarithms of frequencies obtained using a robust generalized zero-crossing method through the gzc function (where the components are simplified into extrema separated by zero-crossings) and instantaneous frequency computed from another method

Usage

gzc.departure(
  pulse = NULL,
  dt = NULL,
  m = NULL,
  f = NULL,
  repl = 1,
  mode = NULL,
  simplify = TRUE
)

Arguments

pulse

a pulse object object

dt

the depth or time. Is overridden by pulse.

m

a matrix of the modes to calculate the gzc frequency from. Is overridden by pulse.

f

a matrix of the frequencies to compare to gzc.

repl

the amount of replicates in m. Is overridden by emd.

mode

the mode sequence index to give to each replicated IMFs. Is overridden by emd.

simplify

whether to average the value for each component of each replicate

Value

If simplify is TRUE, the function returns the average gzc departure as a data frame where the columns stand for the modes and the rows for the replicates. If simplify if FALSE, the function returns the functions returns local gzc departure.

Examples

# NOT RUN {
set.seed(42)

n <- 600
t <- seq_len(n)

p1 <- 30
p2 <- 240

xy <- (1 + 0.6 * sin(t*2*pi/p2)) * sin(t*2*pi/p1)  + 2 * sin(t*2*pi/p2) +
  rnorm(n, sd = 0.5) + t * 0.01

inter_dt <- round(runif(length(xy), min = 0.5, max = 1.5),1)

dt <- cumsum(inter_dt)

dec1 <- extricate(xy, dt, nimf = 5, repl = 1, comb = 10, sifting = 1,
                 factor_noise = 10, bind = TRUE, speak = TRUE)

dec2 <- extricate(xy, dt, nimf = 6, repl = 1, comb = 100, sifting = 5,
                  factor_noise = 50, bind = TRUE, speak = TRUE)

# }
# NOT RUN {
plot_emd(dec1, name = "EMD 1", dir = tempdir())
plot_emd(dec2, name = "EMD 2", dir = tempdir())
# }
# NOT RUN {
parsimony(dec1)
parsimony(dec2)

f1 <- inst.pulse(dec1, plot = FALSE)
f2 <- inst.pulse(dec2, plot = FALSE)

gzc.departure(f1)
gzc.departure(f2)

# }