Using deep neural networks to improve the precision of fast-sampled particle timing detectors

• Autorzy: Kocot Mateusz , Misan Krzysztof , Avati Valentina , Bossini Edoardo , Grzanka Leszek , Minafra Nicola

Identyfikatory

DOI

10.7494/csci.2024.25.1.5784

• Języki publikacji: EN

Abstrakty

EN

Measurements from particle timing detectors are often affected by the time walk effect caused by statistical fluctuations in the charge deposited by passing particles. The constant fraction discriminator (CFD) algorithm is frequently used to mitigate this effect both in test setups and in running experiments, such as the CMS-PPS system at the CERN’s LHC. The CFD is simple and effective but does not leverage all voltage samples in a time series. Its performance could be enhanced with deep neural networks, which are commonly used for time series analysis, including computing the particle arrival time. We evaluated various neural network architectures using data acquired at the test beam facility in the DESY-II synchrotron, where a precise MCP (MicroChannel Plate) detector was installed in addition to PPS diamond timing detectors. MCP measurements were used as a reference to train the networks and compare the results with the standard CFD method. Ultimately, we improved the timing precision by 8% to 23%, depending on the detector’s readout channel.The best results were obtained using a UNet-based model, which out performed classical convolutional networks and the multilayer perceptron.

Słowa kluczowe

EN

deep neural network; timing detectors; iamond sensors; time series analysis; time walk correction; CERN; Precision Proton Spectrometer

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2024
• Tom: T. 25 (1)
• Strony: 43--61
• Opis fizyczny: Bibliogr. 28 poz., rys., tab., wykr.

Twórcy

autor

Kocot Mateusz

• AGH University of Krakow, Krakow, Poland

autor

Misan Krzysztof

• AGH University of Krakow, Krakow, Poland

autor

Avati Valentina

• AGH University of Krakow, Krakow, Poland

autor

Bossini Edoardo

• INFN Sezione di Pisa, Pisa, Italy

autor

Grzanka Leszek

• AGH University of Krakow, Krakow, Poland

autor

Minafra Nicola

• University of Kansas, Department of Physics and Astronomy, Lawrence, KS, United States

Bibliografia

• [1] Albrow M., Arneodo M., Avati V., Baechler J., Cartiglia N., Deile M., Gallinaro M., et al.: CMS-TOTEM Precision Proton Spectrometer, Technical designreport CMS:13, Technical design report TOTEM:3 13, 2014. https://cds.cern.ch/record/1753795/.
• [2] Azzolin V., Andrews M., Cerminara G., Dev N., Jessop C., Marinelli N., Mudholkar T.,et al.: Improving data quality monitoring via a partnership of technologies and resources between the cms experiment at cern and industry. In: EPJWeb of Conferences, vol. 214, 01007, 2019. doi: 10.1051/epjconf/201921401007.
• [3] Bauerle A., Onzenoodt van C., Ropinski T.: Net2Vis – A Visual Grammarfor Automatically Generating Publication-Tailored CNN Architecture Visualizations, IEEE Transactions on Visualization and Computer Graphics, vol. 27(6), pp. 2980–2991, 2021. doi: 10.1109/TVCG.2021.3057483.
• [4] Berg E., Cherry S.R.: Using convolutional neural networks to estimate time-of-flight from PET detector waveforms, Physics in Medicine&Biology, vol. 63(2),02LT01, 2018.
• [5] Berretti M., Bossini E., Minafra N.: Timing performances of diamond detectors with Charge Sensitive Amplifier readout, Technical report, CERN-TOTEM-NOTE-2015-003, 2015. https://cds.cern.ch/record/2055747.
• [6] Bossini E.:Development of a Time Of Flight diamond detector and readout system for the TOTEM experiment at CERN, Ph.D. thesis, INFN, Siena, 2016. https://cds.cern.ch/record/2227688. CERN-THESIS-2016-137.
• [7] Bossini E.: The CMS Precision Proton Spectrometer timing system: performancein Run 2, future upgrades and sensor radiation hardness studies, Journal of Instrumentation, vol. 15(05), C05054, 2020. doi: 10.1088/1748-0221/15/05/C05054.
• [8] Bossini E., Figueiredo D.M., Forthomme L.M., Garcia Fuentes F.I.: Test beamresults of irradiated single-crystal CVD diamond detectors at DESY-II, Technicalreports, CMS-NOTE-2020-007, CERN-CMS-NOTE-2020-007, 2020.
• [9] Breton D., De Cacqueray V., Delagnes E., Grabas H., Maalmi J., Minafra N.,Royon C., Saimpert M.: Measurements of timing resolution of ultra-fast silicon detectors with the SAMPIC waveform digitizer, Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, vol. 835, pp. 51–60, 2016. doi: 10.1016/j.nima.2016.08.019.
• [10] Caruana R., Lawrence S., Giles C.: Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping, Advances in Neural Information Processing Systems, vol. 13, 2000.
• [11] Delagnes E., Breton D., Grabas H., Maalmi J., Rusquart P., Saimpert M.: The SAMPIC waveform and time to digital converter. In: 2014 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), pp. 1–9, IEEE, 2014. doi: 10.1109/nssmic.2014.7431231.
• [12] Evans L., Bryant P.: LHC machine, Journal of Instrumentation, vol. 3(08), S08001, 2008. doi: 10.1088/1748-0221/3/08/S08001.
• [13] Glorot X., Bordes A., Bengio Y.: Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTAT), pp. 315–323, JMLR Workshop and Conference Proceedings, 2011.
• [14] Ioffe S., Szegedy C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML’15: Proceedings of the 32nd International Conference on International Conference on Machine Learning pp. 448–456, 2015.
• [15] Kingma D.P., Ba J.: Adam: A method for stochastic optimization, arXiv preprintarXiv: 14126980, 2014. doi: 10.48550/arXiv.1412.6980.
• [16] O’Malley T., Bursztein E., Long J., Chollet F., Jin H., Invernizzi L., et al.: KerasTuner, https://github.com/keras-team/keras-tuner, 2019.
• [17] Ronneberger O., Fischer P., Brox T.: U-net: Convolutional networks forbiomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp. 234–241, Springer, 2015.doi: 10.1007/978-3-319-24574-428.
• [18] Schefer M.M.: Machine Learning Techniques for selecting Forward Electrons(2.5<|η|<3.2) with the ATLAS High Level Trigger, Technical report, ATL-DAQ-PROC-2023-001, 2023. https://cds.cern.ch/record/2851302.
• [19] Shlomi J., Battaglia P., Vlimant J.R.: Graph neural networks in particle physics, Machine Learning: Science and Technology, vol. 2(2), 021001, 2020. doi: 10.1088/2632-2153/abbf9a.
• [20] Sodmann P., Vollmer M., Nath N., Kaderali L.: A convolutional neural network for ECG annotation as the basis for classification of cardiac rhythms, Physiological Measurement, vol. 39(10), 104005, 2018.
• [21] Song X., Liu Y., Xue L., Wang J., Zhang J., Wang J., Jiang L., Cheng Z.: Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model, Journal of Petroleum Science and Engineering, vol. 186,106682, 2020.
• [22] Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R.: Drop out: a simple way to prevent neural networks from overfitting, The Journalof Machine Learning Research, vol. 15(1), pp. 1929–1958, 2014.
• [23] The CMS Collaborationet al, Journal of Instrumentation, vol. 3, S08004, 2008.doi: 10.1088/1748-0221/3/08/S08004.
• [24] Tompson J., Goroshin R., Jain A., LeCun Y., Bregler C.: Efficient object localization using convolutional networks. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 648–656, 2015. doi: 10.1109/cvpr.2015.7298664.
• [25] Tompson J.J., Jain A., LeCun Y., Bregler C.: Joint training of a convolutional network and a graphical model for human pose estimation, Advances in Neural Information Processing Systems, vol. 27, 2014. doi: 10.48550/arXiv.1406.2984.
• [26] Wang F., Han D., Wang Y.: Improving the time resolution of the MRPC detectorusing deep-learning algorithms, Journal of Instrumentation, vol. 15(09), C09033,2020. doi: 10.1088/1748-0221/15/09/C09033.
• [27] Wang F., Han D., Wang Y., Yu Y., Lyu P., Guo B.: The study of a newtime reconstruction method for MRPC read out by wave form digitizer, Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, vol. 954, 161224, 2020.doi: 10.1016/j.nima.2018.09.059.
• [28] Zahid M.U., Kiranyaz S., Ince T., Devecioglu O.C., Chowdhury M.E., KhandakarA., Tahir A., Gabbouj M.: Robust R-Peak Detection in Low-Quality Holter ECGsUsing 1D Convolutional Neural Network,IEEE Transactions on Biomedical En-gineering, vol. 69(1), pp. 119–128, 2022. doi: 10.1109/tbme.2021.3088218.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).