Hauptseite > Publikationsdatenbank > Machine Learning for Track Finding at PANDA > print

001     868236
005     20210130004155.0
024 7 _ |a arXiv:1910.07191
|2 arXiv
024 7 _ |a 2128/23713
|2 Handle
024 7 _ |a altmetric:68789088
|2 altmetric
037 _ _ |a FZJ-2019-06797
088 1 _ |a PROC-CTD19-091
088 _ _ |a PROC-CTD19-091
|2 Other
100 1 _ |a Esmail, W.
|0 P:(DE-Juel1)174149
|b 0
|u fzj
111 2 _ |a Connecting the Dots and Workshop on Intelligent Trackers (CTD/WIT2019)
|c Valencia
|d 2019-04-02 - 2019-04-05
|w Spain
245 _ _ |a Machine Learning for Track Finding at PANDA
260 _ _ |c 2019
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a Other
|2 DataCite
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a conferenceObject
|2 DRIVER
336 7 _ |a Report
|0 PUB:(DE-HGF)29
|2 PUB:(DE-HGF)
|m report
336 7 _ |a LECTURE_SPEECH
|2 ORCID
336 7 _ |a Conference Presentation
|b conf
|m conf
|0 PUB:(DE-HGF)6
|s 1576750061_22300
|2 PUB:(DE-HGF)
|x Other
520 _ _ |a We apply deep learning methods as a track finding algorithm to the PANDA Forward Tracking Stations (FTS). The problem is divided into three steps: The first step relies on an Artificial Neural Network (ANN) that is trained as a binary classifier to build track segments in three different parts of the FTS, namely FT1,FT2, FT3,FT4, and FT5,FT6. The ANN accepts hit pairs as an input and outputs a probability that they are on the same track or not. The second step builds 3D track segments from the 2D ones and is based on the geometry of the detector. The last step is to match the track segments from the different parts of the FTS to form a full track candidate, and is based on a Recurrent Neural Network (RNN). The RNN is used also as a binary classifier that outputs the probability that the combined track segments are a true track or not. The performance of the algorithm is judged based on the purity, efficiency and the ghost ratio of the reconstructed tracks. The purity specifies which fraction of hits in one track come from the correct particle. The correct particle is the particle, which produces the majority of hits in the track. The efficiency is defined as the ratio of the number of correctly reconstructed tracks to all generated tracks.
536 _ _ |a 6G12 - FAIR (POF3-624)
|0 G:(DE-HGF)POF3-6G12
|c POF3-624
|f POF III
|x 0
588 _ _ |a Dataset connected to arXivarXiv
700 1 _ |a Stockmanns, T.
|0 P:(DE-Juel1)131347
|b 1
|u fzj
700 1 _ |a Ritman, J.
|0 P:(DE-Juel1)131301
|b 2
|e Corresponding author
|u fzj
856 4 _ |y OpenAccess
|u https://juser.fz-juelich.de/record/868236/files/1910.07191.pdf
856 4 _ |y OpenAccess
|x pdfa
|u https://juser.fz-juelich.de/record/868236/files/1910.07191.pdf?subformat=pdfa
909 C O |o oai:juser.fz-juelich.de:868236
|p openaire
|p open_access
|p VDB
|p driver
|p dnbdelivery
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-Juel1)174149
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 1
|6 P:(DE-Juel1)131347
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 2
|6 P:(DE-Juel1)131301
913 1 _ |a DE-HGF
|b Forschungsbereich Materie
|l Von Materie zu Materialien und Leben
|1 G:(DE-HGF)POF3-620
|0 G:(DE-HGF)POF3-624
|2 G:(DE-HGF)POF3-600
|v Facility topic: Physics and materials science with ion beams
|9 G:(DE-HGF)POF3-6G12
|x 0
|4 G:(DE-HGF)POF
|3 G:(DE-HGF)POF3
914 1 _ |y 2019
915 _ _ |a OpenAccess
|0 StatID:(DE-HGF)0510
|2 StatID
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)IKP-1-20111104
|k IKP-1
|l Experimentelle Hadronstruktur
|x 0
980 _ _ |a conf
980 _ _ |a VDB
980 _ _ |a UNRESTRICTED
980 _ _ |a report
980 _ _ |a I:(DE-Juel1)IKP-1-20111104
980 1 _ |a FullTexts

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21