2D and 3D marked point clouds (as earthquake hypocenters) are clustered as principal curves and principal surfaces (to detect tectonic faults), using local means and principal components of the local covariance matrices of the points. The toolbox provides basic estimation algorithms in 2D and 3D and methods for tentative automatic hyperparameter selection, such as the local sample size (n nearest neighbors) and the number if iterations.
Principal Component Local Mean Clustering of Spatial Data
Grillenzoni, Carlo
Software
2023-01-01
Abstract
2D and 3D marked point clouds (as earthquake hypocenters) are clustered as principal curves and principal surfaces (to detect tectonic faults), using local means and principal components of the local covariance matrices of the points. The toolbox provides basic estimation algorithms in 2D and 3D and methods for tentative automatic hyperparameter selection, such as the local sample size (n nearest neighbors) and the number if iterations.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
