Ústav technické a experimentální fyziky Institute of Experimental and Applied Physics

TPC track denoising and recognition using convolutional neural networks

NázevTitle
TPC track denoising and recognition using convolutional neural networksTPC track denoising and recognition using convolutional neural networks
Druh výsledkuResult type
Článek v časopiseJournal article
AutořiAuthors
M. Gajdoš, H.N. da Luz, G.G.A. Souza, M. Bregant
DOIDOI
10.1016/j.cpc.2025.109608
Časopis / citaceJournal / citation
Computer Physics Communications. 2025, 312 1-9. ISSN 0010-4655.
RokYear
2025
JazykLanguage
eng
WoSWoS
001466537600001
ScopusScopus
2-s2.0-105001814599
RIVRIV
RIV/68407700:21670/25:00383215!RIV26-MSM-21670___
ProjektProject
Institucionální podpora na rozvoj výzkumné org.Institucionální podpora na rozvoj výzkumné org.

AbstraktAbstract

The capability of convolutional neural networks to remove spurious signals caused by electronic noise, microdischarges and other effects from experimental data obtained with Time Projection Chambers is studied. A generator of synthetic data for the training of the neural network is described and its performance is compared with the results obtained with a conventional algorithm. The Physical meaning of the data resulting from the neural network and conventional denoising algorithms is thoroughly analysed, demonstrating the potential of convolutional neural networks in the preparation of raw data for analysis

The capability of convolutional neural networks to remove spurious signals caused by electronic noise, microdischarges and other effects from experimental data obtained with Time Projection Chambers is studied. A generator of synthetic data for the training of the neural network is described and its performance is compared with the results obtained with a conventional algorithm. The Physical meaning of the data resulting from the neural network and conventional denoising algorithms is thoroughly analysed, demonstrating the potential of convolutional neural networks in the preparation of raw data for analysis