Pulse discrimination with a Gaussian mixture model on an FPGA
Abstract
A Gaussian Mixture Model (GMM) based machine learning algorithm has been applied to the problem of gamma/neutron pulse shape discrimination (PSD). The algorithm has been successfully implemented on a standard PC as well as a field programmable gate array (FPGA). We describe the GMM classifier and its implementation on these two different types of hardware. We compare the performance of the algorithm on these two platforms against each other, along with other standard techniques applied in PSD. Our results show that the FPGA-based GMM classifier outperforms the standard PSD techniques in terms of classification accuracy at low particle energy and executes more quickly than its CPU-based counterpart.
- Authors:
-
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States). Computational Engineering Division
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States). Physics Division
- Publication Date:
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation
- OSTI Identifier:
- 1474377
- Alternate Identifier(s):
- OSTI ID: 1582956
- Report Number(s):
- LLNL-JRNL-746701
Journal ID: ISSN 0168-9002; 931194
- Grant/Contract Number:
- AC52-07NA27344
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment
- Additional Journal Information:
- Journal Volume: 900; Journal Issue: C; Journal ID: ISSN 0168-9002
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 73 NUCLEAR PHYSICS AND RADIATION PHYSICS; 97 MATHEMATICS AND COMPUTING; Pulse shape discrimination; Gaussian mixture model; Neutron detection; Field-programmable gate array
Citation Formats
Simms, Lance M., Blair, Brenton, Ruz, Jaime, Wurtz, Ron, Kaplan, Alan D., and Glenn, Andrew. Pulse discrimination with a Gaussian mixture model on an FPGA. United States: N. p., 2018.
Web. doi:10.1016/j.nima.2018.05.039.
Simms, Lance M., Blair, Brenton, Ruz, Jaime, Wurtz, Ron, Kaplan, Alan D., & Glenn, Andrew. Pulse discrimination with a Gaussian mixture model on an FPGA. United States. https://doi.org/10.1016/j.nima.2018.05.039
Simms, Lance M., Blair, Brenton, Ruz, Jaime, Wurtz, Ron, Kaplan, Alan D., and Glenn, Andrew. Wed .
"Pulse discrimination with a Gaussian mixture model on an FPGA". United States. https://doi.org/10.1016/j.nima.2018.05.039. https://www.osti.gov/servlets/purl/1474377.
@article{osti_1474377,
title = {Pulse discrimination with a Gaussian mixture model on an FPGA},
author = {Simms, Lance M. and Blair, Brenton and Ruz, Jaime and Wurtz, Ron and Kaplan, Alan D. and Glenn, Andrew},
abstractNote = {A Gaussian Mixture Model (GMM) based machine learning algorithm has been applied to the problem of gamma/neutron pulse shape discrimination (PSD). The algorithm has been successfully implemented on a standard PC as well as a field programmable gate array (FPGA). We describe the GMM classifier and its implementation on these two different types of hardware. We compare the performance of the algorithm on these two platforms against each other, along with other standard techniques applied in PSD. Our results show that the FPGA-based GMM classifier outperforms the standard PSD techniques in terms of classification accuracy at low particle energy and executes more quickly than its CPU-based counterpart.},
doi = {10.1016/j.nima.2018.05.039},
journal = {Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment},
number = C,
volume = 900,
place = {United States},
year = {Wed May 23 00:00:00 EDT 2018},
month = {Wed May 23 00:00:00 EDT 2018}
}
Web of Science
Figures / Tables:
Figures / Tables found in this record: