請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71514
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 王名儒(Ming-Zu Wang) | |
dc.contributor.author | Chia-Te Chen | en |
dc.contributor.author | 陳家德 | zh_TW |
dc.date.accessioned | 2021-06-17T06:02:14Z | - |
dc.date.available | 2019-02-14 | |
dc.date.copyright | 2019-02-14 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-01-30 | |
dc.identifier.citation | [1] Abashian et al., The Belle detector, Nucl. Instrum. Meth. A479 (2002) 117.
[2] Andreas Moll, The Software Framework of the Belle II Experiment, 2011 J. Phys.: Conf. Ser. 331 032024 [3] A. Krizhevsky. Convolutional deep belief networks on cifar-10. Unpublished manuscript, 2010. [4] A. Krizhevsky., Sutskever, I., and Hinton, G. E. ImageNet classification with deep convolutional neural networks. In NIPS, pp. 1106–1114, 2012. [5] Belle-II collaboration, T. Abe et al., Belle II technical design report, KEK-REPORT-2010-1 [arXiv:1011.0352]. [6] H. Ikeda, Development of the CsI(Tl) calorimeter for the measurement of CP violation at KEK B-Factory, Ph.D. Thesis, Nara Women's University, 1999. [7] H. Ikeda et al., A detailed test of the CsI(Tl) calorimeter for BELLE with photon beams of energy between 20 MeV and 5.4 GeV, Nuclear Instruments and Methods in Physics Research A 441 (2000) 401-426 [8] Huber. P. J, Robust Estimation of a Location Parameter. 1964, Ann. Math. Statist. 3573101 [9] Kingma, Diederik P. and Ba, Jimmy. Adam: A Method for Stochastic Optimization, 2014. arXiv:1412.6980 [cs.LG] [10] K. Miyabayashi et al., Upgrade of the Belle II electromagnetic calorimeter, 2014 JINST 9 P09011. [11] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86, 2278–2324. [12] M. Abadi, A. Agarwal et al., 'Tensorflow: Large-scale machine learning on heterogeneous distributed systems', 2016. [13] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift., 2015 In Proceedings of ICML, pages 448–456. [14] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Machine Learning Res. 15, 1929–1958 (2014). [15] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. Going deeper with convolutions. CoRR, abs/1409.4842, 2014. [16] T. Ferber, π0 and η in BelleII data, May, 2018. BELLE2-NOTE-NEUTRALS-01 [17] The LHCb Collaboration et al., The LHCb Detector at the LHC ,2008 JINST 3 S08005 [18] V. Aulchenko et al., Electromagnetic calorimeter for Belle II, J. Phys. Conf. Ser. 587 (2015) 012045 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71514 | - |
dc.description.abstract | 在Belle II 實驗中,CsI晶體構成的電磁量能儀[18]被用來偵測光子的能量。然而,能量滲出導致的損失降低了偵測器的準確度。這些能量滲出是晶體之間無反應的區域以及粒子穿透晶體等原因導致的。
探討了電磁量能儀中能量的散布,我們相信這些能量滲出能透過研究沉積能量的分佈模式來進行修正。根據這個想法,我們將沉積能量的分佈以二維圖片的方式表現出來,並且利用卷積神經網路的圖形辨識能力來進行能量修正。 在使用模擬資料進行訓練以及驗證後,我們得到了極具發展性的結果。我們希望在經過更進一步的研究和訓練後,此種修正方法也可以應用在真實資料上。 | zh_TW |
dc.description.abstract | For ECL in Belle II experiment [18], CsI crystals are used to detect photon energy. However, the energy loss caused by leakage decrease the accuracy of the detector. Leakage exists because of non-sensitive region between the scintillator crystals, and the particle penetration through the crystals.
By considering the energy distribution of ECL, we believe that these leakages can be corrected by studying the patterns of distribution of deposited energy. Based on this idea, we represent the distribution of deposited energy as a 2-D image, and correct the energy loss with the pattern recognition ability of convolutional neural network. We got promising result from training and validating CNN model with simulation data. With further studying and training, we hope this kind of correction can apply on real data as well. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T06:02:14Z (GMT). No. of bitstreams: 1 ntu-108-R05245013-1.pdf: 3112949 bytes, checksum: 9b5b4580ed99b6acb2d3811b5eb34bde (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | Acknowledgement 1
Chinese abstract 2 English abstract 3 1. Introduction for Belle II ECL 10 1-1. The Belle II detector 11 1-2. ECL in Belle II 12 1-3. Energy leakage of ECL 14 2. Introduction for CNN 16 2-1. Basic about neural network 16 2-2. Basic about convolutional neural network 17 3. Method 20 3-1. Dataset 20 3-2. Discussion about the input data 23 3-3. Model structure 24 3-3-1. Usage of 1x1 filter 24 3-3-2. Overlapping pooling layers 25 3-3-3. Data augmentation 26 3-3-4. Batch-normalization 26 3-3-5. Dropout 27 3-3-6. Loss function 28 3-3-7. Activation function 28 3-4. Training step 29 3-5. Validation 29 4. Result 31 4-1. Photon energy from a particle gun with photon energy correction 31 4-2. π0 reconstruction with photon energy correction 36 5. Conclusion 38 Reference 39 Appendix A 41 Appendix B 43 | |
dc.language.iso | en | |
dc.title | 利用捲積神經網路進行Belle II ECL之能量修正 | zh_TW |
dc.title | The Energy Correction of Belle II ECL detector by Using Convolutional Neural Network | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 徐靜戈(Jing-Ge Shiu),張寶棣(Pao-Ti Chang),張敏娟 | |
dc.subject.keyword | Belle II實驗,ECL偵測器,卷積神經網路, | zh_TW |
dc.subject.keyword | Belle II experiment,ECL detector,convolutional neural network, | en |
dc.relation.page | 50 | |
dc.identifier.doi | 10.6342/NTU201900280 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-01-30 | |
dc.contributor.author-college | 理學院 | zh_TW |
dc.contributor.author-dept | 應用物理研究所 | zh_TW |
顯示於系所單位: | 應用物理研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 3.04 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。