English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Characterizing uncertainty is a common issue in nuclear measurement and hasimportant implications for reliable physical discovery. Traditional methods areeither insufficient to cope with the heterogeneous nature of uncertainty orinadequate to perform well with unknown mathematical models. In this paper, wepropose using multi-layer convolutional neural networks for empiricaluncertainty estimation and feature extraction of nuclear pulse signals. Thismethod is based on deep learning, a recent development of machine learningtechniques, which learns the desired mapping function from training data andgeneralizes to unseen test data. Furthermore, ensemble learning is utilized toestimate the uncertainty originating from trainable parameters of the networkand to improve the robustness of the whole model. To evaluate the performanceof the proposed method, simulation studies, in comparison with curve fitting,investigate extensive conditions and show its universal applicability. Finally,a case study is made using data from a NICA-MPD electromagnetic calorimetermodule exposed to a test beam at DESY, Germany. The uncertainty estimationmethod successfully detected out-of-distribution samples and also achieved goodaccuracy in time and energy measurements.

Universal uncertainty estimation for nuclear detector signals with neural networks and ensemble learning