I. Kharuk (Avtor), R. U. Abbasi (Avtor), T. Abu-Zayyad (Avtor), M. Allen (Avtor), Yasuhiko Arai (Avtor), R. Arimura (Avtor), E. Barcikowski (Avtor), J. W. Belz (Avtor), D. R. Bergman (Avtor), S. A. Blake (Avtor), J. P. Lundquist (Avtor)

Povzetek

We report on an improvement of deep learning techniques used for identifying primary particles of atmospheric air showers. The progress was achieved by using two neural networks. The first works as a classifier for individual events, while the second predicts fractions of elements in an ensemble of events based on the inference of the first network. For a fixed hadronic model, this approach yields an accuracy of 90% in identifying fractions of elements in an ensemble of events.

Ključne besede

Telescope Array;indirect detection;ground array;cosmic rays;surface detection;ultra-high energy;

Podatki

Jezik: Angleški jezik
Leto izida:
Tipologija: 1.08 - Objavljeni znanstveni prispevek na konferenci
Organizacija: UNG - Univerza v Novi Gorici
UDK: 539.1
COBISS: 166306563 Povezava se bo odprla v novem oknu
ISSN: 1824-8039
Št. ogledov: 27
Št. prenosov: 0
Ocena: 0 (0 glasov)
Metapodatki: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Ostali podatki

Vrsta dela (COBISS): Delo ni kategorizirano
Strani: str. 1-6
Čas izdaje: 2022
DOI: 10.22323/1.395.0384
ID: 20010300