lle_sound: Example application on a soundfile.

In lle: Locally linear embedding

Description

Performs the LLE alogrithm on a sound(file). As a first step, the sound is scanned piecewice with time windows sized t. In every scanning step, the time windows is shifted by dt. This generates an overall data set with dimension n=t and sample size N\approxt/dt. This dataset can then be embedded using LLE algorithm.

Usage

 lle_sound(t = 500, dt = 20, k = 25, reg = 2, ss = FALSE, 
                   p = 0.5, id = TRUE) 

Arguments

t	time window used to scan.
dt	time window shift.
k	number of neighbours. See lle.
reg	regularisation method. See lle.
ss	a logical values indicating wheather to perform subset selection. See calc_k.
p	amount of data remaining after subset selection. See lle.
id	a logical values indicating wheather to calculate the intrinsic dimension. See lle.

Examples

    ## Not run: 
	lle_sound()
	lle_sound( 200, 20, 20 )
    
## End(Not run)

lle documentation built on May 2, 2019, 2:49 p.m.