How can i add 20% additive guassian noise to each and every element of vector

20 次查看（过去 30 天）
Fiaz Ahmad
Fiaz Ahmad 2016-5-14
回答： Bjorn Gustavsson 2016-5-14
Suppose i have a fixed value vector a=[1.05;0.2561;.3321]). I want to add 20% Gaussian noise to each value of this vector as follows:
a_with_noise=[a]+[20% Gaussian noise]=====> This should give me; a_with_noise=[1.05+noise;0.2561+noise;.3321+noise]
Here [a] should act as the mean of the Gaussian noise distribution.
Thanks

请先登录，再回答此问题。

采纳的回答

Image Analyst
Image Analyst 2016-5-14
There is a function called randn() that you must have overlooked when you were searching for "random" in the help. Use that. It gives noise with zero mean and unit standard deviation so you'll have to scale it:
% Define our signal - a column vector.
a=[1.05;0.2561;.3321]
% Make the spread of the Gaussians be 20% of the a values
sigmas = 0.2 * a % Also a column vector.
% Create the noise values that we'll add to a.
randomNoise = randn(length(a), 1) .* sigmas
% Add noise to a to make an output column vector.
output = a + randomNoise

更多回答（1 个）

Bjorn Gustavsson
Bjorn Gustavsson 2016-5-14
If I get you right this should do it:
function A_p_noise = addgaussiannoise(A,N2S)
A_p_noise = A.*(1+N2S*randn(size(A)));
HTH

类别

在 Help Center 和 File Exchange 中查找有关 Random Number Generation 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by