This is an implementation of the Bayesian Online Changepoint Detection algorithm (described in this paper) in MATLAB. It is heavily inspired from Gregory Gundersen's Python implementation of the same (blog post linked here, and the GitHub repo is linked here).
In this implementation, since the mean and variance of the data are unknown, a normal gamma prior has been used.
All the resources used to make this implementation possible are saved in sources.txt
. NMRlogWell.mat
contains the data that was used to verify whether the algorithm works as intended.