Applying Bayesian Neural Networks to Event Reconstruction in Reactor Neutrino Experiments

Ye Xu; Weiwei Xu; Yixiong Meng; Kaien Zhu; Wei Xu

doi:10.1016/j.nima.2008.04.006

Applying Bayesian Neural Networks to Event Reconstruction in Reactor Neutrino Experiments

Data Analysis, Statistics and Probability 2011-05-05 v3 High Energy Physics - Experiment Instrumentation and Detectors

Authors: Ye Xu , Weiwei Xu , Yixiong Meng , Kaien Zhu , Wei Xu

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

A toy detector has been designed to simulate central detectors in reactor neutrino experiments in the paper. The electron samples from the Monte-Carlo simulation of the toy detector have been reconstructed by the method of Bayesian neural networks (BNN) and the standard algorithm, a maximum likelihood method (MLD), respectively. The result of the event reconstruction using BNN has been compared with the one using MLD. Compared to MLD, the uncertainties of the electron vertex are not improved, but the energy resolutions are significantly improved using BNN. And the improvement is more obvious for the high energy electrons than the low energy ones.

Keywords

Bayesian neural networks event reconstruction reactor neutrino experiments energy resolution maximum likelihood method Monte-Carlo simulation

Cite

@article{arxiv.0712.4042,
  title  = {Applying Bayesian Neural Networks to Event Reconstruction in Reactor Neutrino Experiments},
  author = {Ye Xu and Weiwei Xu and Yixiong Meng and Kaien Zhu and Wei Xu},
  journal= {arXiv preprint arXiv:0712.4042},
  year   = {2011}
}

Comments

9 pages, 3 figures, Accepted by NIMA

Applying Bayesian Neural Networks to Event Reconstruction in Reactor Neutrino Experiments

Abstract

Keywords

Cite

Comments

Related papers