2015/05/03 by P. Płoński, Płoński, Piotr, Dorota Stefan +5
Physics and Astronomy · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Physical sciences #Instrumentation and Detectors (physics.ins-det) #Neutrino Physics Research #Particle Detector Development and Performance #Radiation Detection and Scintillator Technologies
paper · pdf · doi:10.48550/arxiv.1505.00424
openalex publication_date 2015/05/03 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28
Neutrinos are one of the least known elementary particles. The detection of\nneutrinos is an extremely difficult task since they are affected only by weak\nsub-atomic force or gravity. Therefore large detectors are constructed to\nreveal neutrino's properties. Among them the Liquid Argon Time Projection\nChamber (LAr-TPC) detectors provide excellent imaging and particle\nidentification ability for studying neutrinos. The computerized methods for\nautomatic reconstruction and identification of particles are needed to fully\nexploit the potential of the LAr-TPC technique. Herein, the novel method for\nelectron neutrino classification is presented. The method constructs a feature\ndescriptor from images of observed event. It characterizes the signal\ndistribution propagated from vertex of interest, where the particle interacts\nwith the detector medium. The classifier is learned with a constructed feature\ndescriptor to decide whether the images represent the electron neutrino or\ncascade produced by photons. The proposed approach assumes that the position of\nprimary interaction vertex is known. The method's performance in dependency to\nthe noise in a primary vertex position and deposited energy of particles is\nstudied.\n