Gaussian mixture models as automated particle classifiers for fast neutron detectors. (25th July 2019)

• Record Type: Journal Article
• Authors: Blair, Brenton; Chen, Cliff; Glenn, Andrew; Kaplan, Alan; Ruz, Jaime; Simms, Lance; Wurtz, Ron
• Other Names: Lawrence Earl guestEditor.
• Is Part Of: Statistical analysis and data mining. Volume 12:Number 6(2019)
• Page Start: 479
• Page End: 488
• Publication Date: 2019-07-25
• Subjects: classification -- clustering -- mixture models -- pulse shape discrimination; Data mining -- Statistical methods -- Periodicals; 006.312
• DOI: 10.1002/sam.11432
• Languages: English
• ISSNs: 1932-1864

Abstract

Abstract: Pulse shape discrimination (PSD) is the task of classifying electronic pulse shapes for different particle types such as gamma rays and fast neutrons interacting in scintillators and read out by photo sensitive detectors. This field has been limited in its adoption of techniques found in the statistical learning community. Methods initially employed in the 1960s for analog electronic circuitry persist in the current PSD literature describing operations performed on digitized pulses, which are amenable to statistical rigor. Despite vast amounts of data collected at low energy levels, traditional PSD methods are unable to discriminate particles below a certain threshold. In this work, Gaussian mixture models (GMMs) are used as a clustering technique for fast neutron detection in the absence of labeled data. GMMs yield improvements spanning the energy spectrum in a desirably efficient, unsupervised fashion. An extension, the Dirichlet Process GMM, provides further flexibility and classification improvement.