Journals of Accelerator Conferences Website (JACoW)
JACoW
is a publisher in Geneva, Switzerland that publishes the
proceedings of accelerator conferences held around the world
by an international collaboration of editors.
| URL | https://doi.org/10.18429/JACoW-IBIC2025-MOPCO36 |
|---|---|
| Title | Application of convolutional neural networks for pile up correction in single particle counting |
| Authors |
|
| Abstract | An exploration into the application of machine learning (ML) approaches to identify pile-ups and correct them in single particle counters at the GSI Helmholtz Centre for Heavy Ion Research in presented. About 100000 particle pulse data from various spills were manually labelled and a convolutional neural network (CNN) was developed to accurately count the number of particles without domain-specific knowledge. This contribution represents proof-of-work for a fast error free automated particle counting system. The identified algorithm was developed with a perspective of implementation into an FPGA. |
| Paper | download: MOPCO36.pdf |
| Cite | BibTeX, LaTeX, Text/Word, RIS, EndNote |
| Conference | 14th International Beam Instrumentation Conference |
| Series | |
| Location | Liverpool, UK |
| Date | 07-11 Sep 2025 |
| Publisher | JACoW Publishing, Geneva, Switzerland |
| Editorial Board | Narender Kumar (Editor-in-Chief) - UoL/CI, UK Robert Apsimon - CI, UK Thankonwat Chanwattana - SLRI, Thailand Zhichu Chen - SARI, China Eunhoon Im - IBS, Korea Jangwon Kwon - IBS, Korea Milaan Patel - UoL/CI, UK Volker RW Schaa - GSI, Germany Jana Thomson -TRIUMF, Canada Bradley Wilson, STFC, UK Hao Zhang, UoL/CI, UK |
| Online ISBN | 978-3-95450-262-2 |
| Online ISSN | 2673-5350 |
| Received | 01 September 2025 |
| Revised | 07 September 2025 |
| Accepted | 07 September 2025 |
| Issued | 20 January 2026 |
| DOI | 10.18429/JACoW-IBIC2025-MOPCO36 |
| Pages | 152-155 |
| Copyright | Published by JACoW Publishing under the terms of the Creative Commons Attribution 4.0 license. Any further distribution of this work must maintain attribution to the author(s), the published article's title, publisher, and DOI. |