University of Illinois Urbana-Champaign

Kernel-based Gaussian process for anomaly detection in sparse gamma-ray data

Romanchek, Gregory R.; Liu, Zheng; Abbaszadeh, Shiva

Permalink

https://hdl.handle.net/2142/106072

Description

Title
Kernel-based Gaussian process for anomaly detection in sparse gamma-ray data
Author(s)
  • Romanchek, Gregory R.
  • Liu, Zheng
  • Abbaszadeh, Shiva
Issue Date
2020-01-23
Keyword(s)
  • Kernel functions
  • Covariance
  • Algorithms
  • Noise reduction
  • Dwell time
  • Machine learning algorithms
  • Gamma spectrometry
  • Gamma rays
Abstract
In radioactive source surveying protocols, a number of task-inherent features degrade the quality of collected gamma ray spectra, including: limited dwell times, a fluctuating background, a large distance to the source, weak source activity, and the low sensitivity of mobile detectors. Thus, collected gamma ray spectra are expected to be sparse and noise dominated. For extremely sparse spectra, direct background subtraction is infeasible and many background estimation techniques do not apply. In this paper, we present a statistical algorithm for source estimation and anomaly detection under such conditions. We employ a fixed-hyperparameter Gaussian processes regression methodology with a linear innovation sequence scheme in order to quickly update an ongoing source distribution estimate with no prior training required. We have evaluated the effectiveness of this approach for anomaly detection using background spectra collected with a Kromek D3S and simulated source spectrum and hyperparameters defined by detector characteristics and information derived from collected spectra. We attained an area under the ROC curve of 0.902 for identifying sparse source peaks within a sparse gamma ray spectrum and achieved a true positive rate of 93% when selecting the optimum thresholding value derived from the ROC curve.
Publisher
PLoS
Series/Report Name or Number
PLoS ONE; vol. 15, no.1, 2020
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/106072
DOI
https://doi.org/10.1371/journal.pone.0228048
Copyright and License Information
Copyright 2020 Gregory R. Romanchek, Zheng Liu, and Shiva Abbaszadeh

Owning Collections

Illinois Research and Scholarship (Open Collection) PRIMARY
This is the default collection for all research and scholarship developed by faculty, staff, or students at the University of Illinois at Urbana-Champaign