000868236 001__ 868236
000868236 005__ 20210130004155.0
000868236 0247_ $$2arXiv$$aarXiv:1910.07191
000868236 0247_ $$2Handle$$a2128/23713
000868236 0247_ $$2altmetric$$aaltmetric:68789088
000868236 037__ $$aFZJ-2019-06797
000868236 0881_ $$aPROC-CTD19-091
000868236 088__ $$2Other$$aPROC-CTD19-091
000868236 1001_ $$0P:(DE-Juel1)174149$$aEsmail, W.$$b0$$ufzj
000868236 1112_ $$aConnecting the Dots and Workshop on Intelligent Trackers (CTD/WIT2019)$$cValencia$$d2019-04-02 - 2019-04-05$$wSpain
000868236 245__ $$aMachine Learning for Track Finding at PANDA
000868236 260__ $$c2019
000868236 3367_ $$033$$2EndNote$$aConference Paper
000868236 3367_ $$2DataCite$$aOther
000868236 3367_ $$2BibTeX$$aINPROCEEDINGS
000868236 3367_ $$2DRIVER$$aconferenceObject
000868236 3367_ $$0PUB:(DE-HGF)29$$2PUB:(DE-HGF)$$aReport$$mreport
000868236 3367_ $$2ORCID$$aLECTURE_SPEECH
000868236 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1576750061_22300$$xOther
000868236 520__ $$aWe apply deep learning methods as a track finding algorithm to the PANDA Forward Tracking Stations (FTS). The problem is divided into three steps: The first step relies on an Artificial Neural Network (ANN) that is trained as a binary classifier to build track segments in three different parts of the FTS, namely FT1,FT2, FT3,FT4, and FT5,FT6. The ANN accepts hit pairs as an input and outputs a probability that they are on the same track or not. The second step builds 3D track segments from the 2D ones and is based on the geometry of the detector. The last step is to match the track segments from the different parts of the FTS to form a full track candidate, and is based on a Recurrent Neural Network (RNN). The RNN is used also as a binary classifier that outputs the probability that the combined track segments are a true track or not. The performance of the algorithm is judged based on the purity, efficiency and the ghost ratio of the reconstructed tracks. The purity specifies which fraction of hits in one track come from the correct particle. The correct particle is the particle, which produces the majority of hits in the track. The efficiency is defined as the ratio of the number of correctly reconstructed tracks to all generated tracks.
000868236 536__ $$0G:(DE-HGF)POF3-6G12$$a6G12 - FAIR (POF3-624)$$cPOF3-624$$fPOF III$$x0
000868236 588__ $$aDataset connected to arXivarXiv
000868236 7001_ $$0P:(DE-Juel1)131347$$aStockmanns, T.$$b1$$ufzj
000868236 7001_ $$0P:(DE-Juel1)131301$$aRitman, J.$$b2$$eCorresponding author$$ufzj
000868236 8564_ $$uhttps://juser.fz-juelich.de/record/868236/files/1910.07191.pdf$$yOpenAccess
000868236 8564_ $$uhttps://juser.fz-juelich.de/record/868236/files/1910.07191.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000868236 909CO $$ooai:juser.fz-juelich.de:868236$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000868236 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)174149$$aForschungszentrum Jülich$$b0$$kFZJ
000868236 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131347$$aForschungszentrum Jülich$$b1$$kFZJ
000868236 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131301$$aForschungszentrum Jülich$$b2$$kFZJ
000868236 9131_ $$0G:(DE-HGF)POF3-624$$1G:(DE-HGF)POF3-620$$2G:(DE-HGF)POF3-600$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF3-6G12$$aDE-HGF$$bForschungsbereich Materie$$lVon Materie zu Materialien und Leben$$vFacility topic: Physics and materials science with ion beams$$x0
000868236 9141_ $$y2019
000868236 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000868236 920__ $$lyes
000868236 9201_ $$0I:(DE-Juel1)IKP-1-20111104$$kIKP-1$$lExperimentelle Hadronstruktur$$x0
000868236 980__ $$aconf
000868236 980__ $$aVDB
000868236 980__ $$aUNRESTRICTED
000868236 980__ $$areport
000868236 980__ $$aI:(DE-Juel1)IKP-1-20111104
000868236 9801_ $$aFullTexts