maad.features.surface_roughness
- maad.features.surface_roughness(x, norm='global')[source]
Compute the surface roughness index of a signal (1D) or a spectrogram (2D).
Surface roughness is quantified by the deviations in the direction of the normal vector of a real surface from its ideal form. If these deviations are large, the surface is rough; if they are small, the surface is smooth [1].
- Parameters:
- xndarray of floats
vector (1d) or matrix (2d)
- normstring, optional, default is ‘global’
Determine if the ROUGHNESS is normalized by the sum of the whole data (‘global’ mode) or by the sum of horizontal line for each line (‘per_bin’)
- Returns:
- Rascalar or 1d ndarray of scalars
if x is a vector => Arithmetical mean deviation of x. if x is a matrix => Arithmetical mean deviation of each line of x.
- Rqscalar or 1d ndarray of scalars
if x is a vector => Root mean squared of deviationn of x. if x is a matrix => Root mean squared of deviation of each line of x.
References
[1]