corona: Ridge Estimation by Corona Method

Description

Estimate a (single) ridge from a time-frequency representation, using the corona method.

Usage

corona(tfrep, guess, tfspec=numeric(dim(tfrep)[2]), subrate=1,
temprate=3, mu=1, lambda=2 * mu, iteration=1000000, seed=-7,
stagnant=20000, costsub=1, plot=T)

Arguments

tfrep

Time-Frequency representation (real valued).

guess

Initial guess for the algorithm.

tfspec

Estimate for the contribution of the noise to modulus.

subrate

Subsampling rate for ridge estimation.

temprate

Initial value of temperature parameter.

Coefficient of the ridge's second derivative in cost function.

lambda

Coefficient of the ridge's derivative in cost function.

iteration

Maximal number of moves.

seed

Initialization of random number generator.

stagnant

Maximum number of stationary iterations before stopping.

costsub

Subsampling of cost function in output.

plot

When set(default), some results will be shown on the display.

Value

Returns the estimated ridge and the cost function.
ridge1D array (of same length as the signal) containing the ridge.
cost1D array containing the cost function.

Warning

The returned cost may be a large array, which is time consuming. The argument costsub allows subsampling the cost function.

Details

To accelerate convergence, it is useful to preprocess modulus before running annealing method. Such a preprocessing (smoothing and subsampling of modulus) is implemented in corona. The parameter subrate specifies the subsampling rate.

References

See discussion in text of ``Practical Time-Frequency Analysis''.