GMM Entropy-based Anomaly Detection
Gaussian mixture modeling is a generative probabilistic model that assumes that the observed data are generated from a mixture of multiple Gaussian distributions. The Gaussian mixture model (GMM) with a noise component refers to a finite mixture that includes an additional noise component to model the background noise or outliers in the data. Scrucca (2023) proposes an entropy-based approach for initial detection of noisy data to be used in an EM algorithm for estimation of Gaussian mixtures with a uniform noise component over the convex hull of the data.
-
This repository contains the R code to reproduce the analyses in the paper:
Scrucca L. (2023) Entropy-based anomaly detection for Gaussian mixture modeling. Algorithms, 16:4, 195. doi: 10.3390/a16040195
-
Instructions:
- open and execute the code contained in the file
examples.R.
- open and execute the code contained in the file