Markov chain Monte Carlo and stochastic origin ensembles methods – Comparison of a simple application for a Compton imager detector

PDF

Authors
  1. Drouin, P.L.
Corporate Authors
Defence Research and Development Canada, Ottawa Research Centre, Ottawa ON (CAN)
Abstract
This document aims to summarise Markov Chain Monte Carlo (MCMC) methods, in particular, the Metropolis-Hastings algorithm and the Stochastic Origin Ensembles (SOE) method, in a concise and notation-consistent manner. These methods are commonly used to perform model parameter estimation for a population, based on a measured sample, through the sampling of the probability distribution for these parameters. A simple application of SOE is then demonstrated using simulation data from a Compton imager detector.

Il y a un résumé en français ici.

Keywords
radiation source localisation;source activity measurement;networked detectors;directional detectors;maximum likelihood;point of closest approach;RadCompass
Report Number
DRDC-RDDC-2016-R124 — Scientific Report
Date of publication
01 Sep 2016
Number of Pages
22
DSTKIM No
CA043184
CANDIS No
804479
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: