Belle II pixeldetector cluster analyses using neural network algorithms

Stephanie Käs ; Jens Sören Lange ; Katharina Dort ; Marvin Peter ; Irina Heinz ; Johannes Bilk ; Peter Lehnhardt ; Johannes Budak ; Falk Zorn

09 March 2021
DPG Spring Meeting 2021

Abstract: The Belle II DEPFET pixeldetector is operating since 2019, presently with 4 M pixels and trigger rates up to 5 kHz. The pixeldetector has the unique ability to detect exotic highly ionizing particles such as antideuterons or stable tetraquarks which due to their high energy loss do not reach the outer sub-detectors, and thus generate no reconstructable track. In order to identify these highly ionizing particles, multivariate analyses of pixeldetector clusters is performed. The multidimensional input space consists of variables such as single pixel signals, cluster observables, or Zernicke moments. We present results for cluster classification using different neural network algorithms: multilayer perceptrons, Convolutional networks, Kohonen-type networks (often denoted as self-organizing maps) and Hopfield-type networks (often denoted as associate memories). Data preprocessing by Principal Components analysis and possible implementation on an FPGA for online reconstruction are discussed as well.

The record appears in these collections:
Talks > Talk Drafts (Internal)
Public Talks

 Record created 2021-04-01, last modified 2021-04-01

Download fulltext

Rate this document:

Rate this document:
(Not yet reviewed)