OPTIMIZATION OF TAU IDENTIFICATION IN ATLAS EXPERIMENT USING MULTIVARIATE TOOLS

Łukasz Janyst, Anna Kaczmarska, Tadeusz Szymocha, Marcin Wolter, Andrzej Zemła

Abstract


Elementary particle physics experiments, which search for very rare processes, require theefficient analysis and selection algorithms able to separate a signal from the overwhelmingbackground. Four learning machine algorithms have been applied to identify τ leptons inthe ATLAS experiment: projective likelihood estimator (LL), Probability Density Estimatorwith Range Searches (PDE-RS), Neural Network, and the Support Vector Machine (SVM).All four methods have similar performance, which is significantly better than the baselinecut analysis. This indicates that the achieved background rejection is close to the maximal achievable performance.

Keywords


multivariate methods; High Energy Physics; ATLAS; tau leptons

Full Text:

PDF

References


Wolter M.: Multivariate analysis methods in physics, Physics of Particles and Nuclei, Volume 38, Issue 2, pp. 255–268, 03/2007

Wolter M., Zemla A.: Optimization of tau identification in ATLAS experiment using multivariate tools, ACAT 07,April 23–27, 2007 Nikhef, Amsterdam, http://pos.sissa.it/

ATLAS collaboration: Detector and Physics Performance Technical Design Report, Volumes 1 and 2, CERN/LHCC/99-14, ATLAS TDR 14, (1999)

Bechtle P. et al.: Identification of hadronic tau decays with ATLAS detector, ATLPHYS- INT-2008-003, ATL-COM-PHYS-2007-066

Kaczmarska A., Richter-Was E., Wolter M., Janyst L.: Performance of the tau1p3p algorithm for hadronic tau decays identification with release 12.0.6, ATLAS Note ATL-PHYS-INT-2008-004; ATL-COM-PHYS-2007-039

https://twiki.cern.ch/twiki/bin/view/Atlas/Tau1P3P

Janyst L., Richter-Was E.: Hadronic tau identification with track based approach: optimisation with multi-variate method, ATL-COM-PHYS-2005-028; Geneva: CERN, 03 Jun 2005

Carli T., Koblitz B.: A multi-variate discrimination technique based on rangesearching, Nucl. Instrum. Meth. A, (501), p. 576, 2003

Bishop C. M.: Neural Networks for Pattern Recognition, Oxford University Press, Oxford, 1995

Zell A. et al : http://www-ra.informatik.uni-tuebingen.de/SNNS/

Werbos P. J.: Beyond regression: new tools for prediction and analysis in the behavioural sciences, Ph.D. thesis, Harvard University, Boston, MA, 1974

Rumelhart D. E., Hinton G. E., Williams R. J.: Learning internal representations by error propagation. Vol. 1 of Computational models of cognition and perception, Cambridge, MA, MIT Press, chap. 8, pp. 319–362, 1986

Vapnik V., Chervonenkis A.: A note on one class of perceptrons. Automation and Remote Control, (25), 1964

Vapnik V., Lerner A.: Pattern recognition using generalized portrait method. Automation and Remote Control, (24), 1963

Boser B., Guyon I., Vapnik V.: A training algorithm for optimal margin classifiers. Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, ACM Press, pp. 144–152, 1992

Cortes C., Vapnik V.: Support vector networks, Machine Learning, (20), pp. 273–297, 1995

Burges C.: A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2), pp. 1–47, 1998

Brun R., Rademakers F.: ROOT – An Object Oriented Data Analysis Framework, Proceedings AIHENP’96 Workshop, Lausanne, Sep. 1996, Nucl. Inst. & Meth. in Phys. Res. A 389 (1997) 81–86. See also http://root.cern.ch

Höcker A., Voss H., Voss K., Stelzer J.: TMVA (Toolkit for MultiVariate Analysis), http://tmva.sourceforge.net

Atlas Collaboration: Atlas Computing Technical Design Report, ATLAS TDR–017, CERN-LHCC-2005-022, 18 March 2005




DOI: https://doi.org/10.7494/csci.2008.9.3.35

Refbacks

  • There are currently no refbacks.