Informace o publikaci
Real-time gamma-neutron discrimination with a trainable polynomial kernel
| Autoři | |
|---|---|
| Rok publikování | 2025 |
| Druh | Článek ve sborníku |
| Konference | EPJ Web Conf. Volume 338, 2025 ANIMMA 2025 – Advancements in Nuclear Instrumentation Measurement Methods and their Applications |
| Fakulta / Pracoviště MU | |
| Citace | |
| www | https://www.epj-conferences.org/articles/epjconf/abs/2025/23/epjconf_animma2025_10004/epjconf_animma2025_10004.html |
| Doi | https://doi.org/10.1051/epjconf/202533810004 |
| Klíčová slova | gamma-neutron discrimination; support vector machines; field-programmable gate array |
| Popis | This paper presents an implementation of gamma-neutron pulse shape discrimination by a support vector machine polynomial decision function in a field-programmable gate array. The training is carried out on a conventional computer using widespread Python libraries. The hardware architecture is designed to allow parameter changes on demand, enabling tuning of hyperparameters and kernel coefficients without requiring re-synthesis. A cubic kernel is compared against a linear kernel which was developed alongside it for non-biased comparison. Both are designed to be viable for real-time classification. The particularities of the designs are explored. The cubic kernel makes use of two stand-alone state machines to keep the sequential data pipelined without interference between the sampled pulses. The results show the trade-off between separation quality, numerical accuracy and physical on-board requirements of the implementations. The separation quality is demonstrated on two datasets, one with a noticeable overlap, to assess any benefits the cubic kernel may bring. |
| Související projekty: |