Show simple item record

dc.contributor.authorGriffiths, J
dc.contributor.authorKleinegesse, S
dc.contributor.authorSaunders, D
dc.contributor.authorTaylor, R
dc.contributor.authorVacheret, A
dc.date.accessioned2022-01-28T16:39:26Z
dc.date.available2022-01-28T16:39:26Z
dc.date.issued2020
dc.date.submitted2020-06-15
dc.identifier.issn2632-2153
dc.identifier.othermlstabb781
dc.identifier.otherabb781
dc.identifier.othermlst-100166.r1
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/333209
dc.description.abstract<jats:title>Abstract</jats:title> <jats:p>We demonstrate the use of a convolutional neural network to perform neutron-gamma pulse shape discrimination, where the only inputs to the network are the raw digitised silicon photomultiplier signals from a dual scintillator detector element made of <jats:sup>6</jats:sup>Li F:ZnS(Ag) scintillator and PVT plastic. A realistic labelled dataset was created to train the network by exposing the detector to an AmBe source, and a data-driven method utilising a separate photomultiplier tube was used to assign labels to the recorded signals. This approach is compared to the charge integration and continuous wavelet transform methods and a simpler artificial neural net. It is found to provide superior levels of discrimination, achieving an area under the curve of 0.996 ± 0.003. We find that the neural network is capable of extracting interpretable features directly from the raw data. In addition, by visualising the high-dimensional representations of the network with the t-SNE algorithm, we discover that not only is this method robust to minor mislabeling of the training dataset but that it is possible to identify an underlying substructure within the signals that goes beyond the original labelling. This technique could be utilised to explore and cluster complex, raw detector data in a novel way that may reveal more insights than standard analysis methods.</jats:p>
dc.languageen
dc.publisherIOP Publishing
dc.subjectPaper
dc.subjectmachine learning
dc.subjectconvolutional neural networks
dc.subjectpulse shape discrimination
dc.subject6Li F:ZnS(Ag)
dc.subjectt-SNE
dc.titlePulse shape discrimination and exploration of scintillation signals using convolutional neural networks
dc.typeArticle
dc.date.updated2022-01-28T16:39:25Z
prism.issueIdentifier4
prism.publicationNameMachine Learning: Science and Technology
prism.volume1
dc.identifier.doi10.17863/CAM.80632
dcterms.dateAccepted2020-09-11
rioxxterms.versionofrecord10.1088/2632-2153/abb781
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0
dc.contributor.orcidVacheret, A [0000-0001-7792-4349]
dc.identifier.eissn2632-2153
pubs.funder-project-idH2020 European Research Council (682474)
cam.issuedOnline2020-10-28


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record