multiSigma: Noise level estimation among multichannel signal

In mwaved: Multichannel Wavelet Deconvolution with Additive Long Memory Noise

Description

Estimates the level of noise (standard deviation of noise) in each channel.

Usage

multiSigma(Y, deg = 3L)

Arguments

Y	An input signal either an n by m matrix containing the multichannel signal to be analysed or single vector of n elements for the single channel. In the multichannel case, each of the m columns represents a channel of n observations.
deg	The degree of the auxiliary polynomial used in the Meyer wavelet.

Details

This function estimates the noise present in each channel by computing the Meyer wavelet transform of each channel of the multichannel signal. In particular, the noise level is computed by using the Median Absolute Deviation (MAD) of the wavelet coefficients at the highest possible resolution at J = floor(log2(n) - 1).

Value

A numeric vector of estimates of the standard deviation of the noise in each of the m channels.

Examples

library(mwaved)
# Simulate matrix of Gaussian variables with three different noise levels
sig <- c(0.25, 0.5, 1.25)
n <- 1024
Y <- sapply(1:3, function(i) sig[i]* rnorm(n))
# Estimate the noise levels
multiSigma(Y, deg = 3)

mwaved documentation built on Oct. 28, 2021, 5:06 p.m.