Yüksek Enerji Fiziğinde Yapay Zeka Tabanlı Makine Öğrenme Yaklaşımı

Yüksek enerjili fizik deneylerinde veri kalitesi, parçacık tanımlamasında önemli bir rol oynar. Parçacık analizinde kullanılan yöntemler, temel olarak uzmanların üst düzey bilgi ve karmaşık hesaplama becerilerine dayanır ve veri kalitesi güvencesi için uzun süre gerektirir. İnsan çabalarının hızını, doğruluğunu ve verimliliğini artırmak için çeşitli alanlarda yapay zeka (AI) uygulamaları önem kazanmaktadır. Bu amaçla, yapay zeka tabanlı makine öğrenmesi yaklaşımı parçacık fiziği analizinde kullanılabilir. Dielektronlar (e-e+), son durum etkileşimlerinin olmamasından dolayı yüksek enerjili çarpışmalarda oluşan ortamın evrimi hakkında bilgi sağlayan elektromanyetik araçlardır. Düşük verimlilikle sonuçlanan geleneksel kesim tabanlı yöntemlerle yüksek saflıkta e-e+ çiftleri elde edilebilir. Bu katkıda dielektron analizinde makine öğrenimi yaklaşımlarının uygulanması tartışılmıştır.

Anahtar Kelimeler:

dielektron, makine öğrenmesi, rastgele orman

Artificial Intelligence Based Machine Learning Approach in High Energy Physics

In high energy physics experiments data quality plays a significant role for particle identification. Methods used in particle analysis are mainly based on high level knowledge and complex computation skills of human experts and require long time for data quality assurance. Artificial intelligence (AI) applications in various fields are getting important to improve the speed, accuracy and efficiency of human efforts. For this purpose, artificial intelligence-based machine learning approach can be used in particle physics analysis. Dielectrons (e-e+) are electromagnetic probes that provide information about evolution of the medium formed in high energy collisions due to lack of final state interactions. A high purity sample of e-e+ pairs can be obtained by traditional cut-based methods resulting in low efficiency. In this contribution, application of machine learning approaches in dielectron analysis is discussed.

Keywords:

Dielectron, machine learning approach, random forest,

PDF

___

Referans1 Markert, C., What do we learn from Resonance Production in Heavy Ion Collisions?, Journal of Physics G: Nuclear and Particle Physics, 31 (4), 169–178, 2005.
Referans2 Torrieri, G. and Rafelski, J., Strange Hadron Resonances as a Signature of Freeze-Out Dynamics, Physics Letters B, 509, 239–245, 2001.
Referans3 Aichelin, J. and Bleicher, M., Strange resonance production: probing chemical and thermal freeze-out in relativistic heavy ion collisions, Physics Letter B, 530, 81–87, 2002.
Referans4 Tawfik, A. and Shalaby, A. G., Balance Function in High-Energy Collisions, Advances in High Energy Physics, 186812, 2015.
Referans5 Rapp, R., Wambach J., Chiral symmetry restoration and dileptons in relativistic heavy-ion collisions, In Advances in Nuclear Physics, 1–205, 2002.
Referans6 Drell, S. D. and Yan, T. M., Massive lepton-pair production in hadron-hadron collisions at high energies, Physical Review Letters, 25(5), 316, 1970.
Referans7 Ho, T. K., The random subspace method for constructing decision forests, IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 832–844, 1998.
Referans8 Trzcinski, T., Graczykowski, L. K. and Glinka, M., Using Random Forest Classifier for particle identification in the ALICE Experiment, Proceedings of Information Technology, Systems Research and Computational Physics, Cracow, 3–17, 2019.
Referans9 Liaw, A. and Wiener, M., Classification and regression by Random Forest, R News, 2, 18–22, 2002.
Referans10 Breiman, L , Random Forests, Machine Learning, 45, 5–32, 2001.
Referans11 Azhari, M., Alaoui, A., Achraoui, Z., Ettaki, B. and Zerouaoui, J., Adaptation of the Random Forest Method, Proceedings of the 4th International Conference on Smart City Applications - SCA ’19, Warsaw, 1141–1146, 2019.
Referans12 Azhari, M., Alaoui, A., Abarda, A., Ettaki, B. and Zerouaoui , J., Using Ensemble Methods to Solve the Problem of Pulsar Search, Big Data and Networks Technologies, Lecture Notes in Networks and Systems, Springer 81, 183-189, 2020.
Referans13 Azhari, M., Alaoui, A., Abarda A., Ettaki, B. and Zerouaoui, J., A Comparison of Random Forest Methods for Solving the Problem of Pulsar Search, Proceedings of the Fourth International Conference on Smart City Applications, Cham, 2020.
Referans14 Introduction to Random Forest in Machine Learning, URL: https://www.section.io/engineering-education/introduction-to-random-forest-in-machine-learning/.
Referans15 McCauley, T., J/psi to two electrons from 2010, CERN Open Data Portal, 2014.
Referans16 McCauley, T., Events with two electrons from 2010, CERN Open Data Portal, 2014.