Abstract
Nowadays, Dark Matter search constitutes one of the most challenging scientific activity. During the last decades several detectors have been developed to evidence the signal of interactions between Dark Matter and ordinary matter. The Argon Dark Matter detector, placed in the Canfranc Underground Laboratory in Spain is the first ton-scale liquid-Ar experiment in operation for Dark Matter direct detection. In parallel to the development of other engineering issues, computational methods are being applied to maximize the exploitation of generated data. In this work, two algorithms based on decision trees —Generalized Boosted Regression Models and Random Forests— are employed to reconstruct the position of the interaction in Argon Dark Matter detector. These two algorithms are confronted to a Montecarlo data set reproducing the physical behaviour of Argon Dark Matter detector. In this work, an in-depth study of the position reconstruction of the interaction is performed for both algorithms, including a study of the distribution of errors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The use of 24 neurons in the input and hidden layers is due to the fact that the ArDM experiment holds 24 photomultipliers. See Sect. 3.1 for further details.
- 2.
In the case of GBM the origin of the patter in the errors is more controversial. Effectively it is associated to the use of this type of decision tree for this dataset. Further research is necessary to explain the origin of pattern shown in Fig. 4
References
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2000)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Kuncheva, L.I.: Ensemble methods. In: Combining Pattern Classifiers: Methods and Algorithms, 2nd edn, pp. 186–229. John Wiley & Sons, Inc. (2014). doi:10.1002/9781118914564.ch6
Pardo, C., Rodríguez, J.J., Díez-Pastor, J.F., García-Osorio, C.: Random oracles for regression ensembles. In: Okun, O., Valentini, G., Re, M. (eds.) Ensembles in Machine Learning Applications. SCI, vol. 373, pp. 181–199. Springer, Heidelberg (2011)
Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)
Ho, T.K.: The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 832–844 (1998)
Montes Nuñez, B.R.: Data Analysis of the Argon Dark Matter Experiment and Background Studies. Ph.D. thesis, Facultad de Ciencias Físicas, Universidad Complutense de Madrid. (2015)
Aprile, E., Angle, J., Arneodo, F., Baudis, L., Bernstein, A., Bolozdynya, A., Brusov, P., Coelho, L., Dahl, C., DeViveiros, L., Ferella, A., Fernandes, L., Fiorucci, S., Gaitskell, R., Giboni, K., Gomez, R., Hasty, R., Kastens, L., Kwong, J., Lopes, J., Madden, N., Manalaysay, A., Manzur, A., McKinsey, D., Monzani, M., Ni, K., Oberlack, U., Orboeck, J., Orlandi, D., Plante, G., Santorelli, R., dos Santos, J., Shagin, P., Shutt, T., Sorensen, P., Schulte, S., Tatananni, E., Winant, C., Yamashita, M.: Design and performance of the XENON10 dark matter experiment. Astropart. Phys. 34(9), 679–698 (2011)
Aprile, E., Arisaka, K., Arneodo, F., Askin, A., Baudis, L., Behrens, A., Brown, E., Cardoso, J., Choi, B., Cline, D., Fattori, S., Ferella, A., Giboni, K., Kish, A., Lam, C., Lang, R., Lim, K., Lopes, J., Undagoitia, T.M., Mei, Y., Fernandez, A.M., Ni, K., Oberlack, U., Orrigo, S., Pantic, E., Plante, G., Ribeiro, A., Santorelli, R., dos Santos, J., Schumann, M., Shagin, P., Teymourian, A., Tziaferi, E., Wang, H., Yamashita, M.: The XENON100 dark matter experiment. Astropart. Phys. 35(9), 573–590 (2012)
Regenfus, C.: The ArDM collaboration: the argon dark matter experiment ArDM. J. Phys.: Conf. Ser. 203(1), 012024 (2010)
Marchionni, A., Amsler, C., Badertscher, A., Boccone, V., Bueno, A., Carmona-Benitez, M.C., Coleman, J., Creus, W., Curioni, A., Daniel, M., Dawe, E.J., Degunda, U., Gendotti, A., Epprecht, L., Horikawa, S., Kaufmann, L., Knecht, L., Laffranchi, M., Lazzaro, C., Lightfoot, P.K., Lussi, D., Lozano, J., Mavrokoridis, K., Melgarejo, A., Mijakowski, P., Natterer, G., Navas-Concha, S., Otyugova, P., de Prado, M., Przewlocki, P., Regenfus, C., Resnati, F., Robinson, M., Rochet, J., Romero, L., Rondio, E., Rubbia, A., Scotto-Lavina, L., Spooner, N.J.C., Strauss, T., Touramanis, C., Ulbricht, J., Viant, T.: ArDM: a ton-scale LAr detector for direct dark matter searches. J. Phys.: Conf. Ser. 308(1), 012006 (2011)
Badertscher, A., et al.: Status of the ArDM Experiment: first results from gaseous argon operation in deep underground environment (2013)
Boccone, V.: The ArDM collaboration: the ArDM project: a liquid argon TPC for dark matter detection. J. Phys.: Conf. Ser. 160(1), 012032 (2009)
Zell, A.: Java Neural Network Simulator (JavaNNS) (2013). http://www.ra.cs.uni-tuebingen.de/software/JavaNNS/
Ridgeway, G.: Generalized boosted models: a guide to the GBM package (2005)
Liaw, A., Wiener, M.: Classification and regression by randomForest. R News 2(3), 18–22 (2002)
Acknowledgment
The research leading to these results has received funding by the Spanish Ministry of Economy and Competitiveness (MINECO) for funding support through the grants FPA2012-30811, FPA2013-47804-C2-1-R, and “Unidad de Excelencia María de Maeztu”: CIEMAT - FÍSICA DE PARTÍCULAS through the grant MDM-2015-0509. The authors acknowledge the kind support of the whole ArDM collaboration by making available the Monte Carlo simulation.
Author information
Authors and Affiliations
Consortia
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Cárdenas-Montes, M., Montes, B., Santorelli, R., Romero, L., on behalf of Argon Dark Matter Collaboration. (2016). Evaluation of Decision Trees Algorithms for Position Reconstruction in Argon Dark Matter Experiment. In: Martínez-Álvarez, F., Troncoso, A., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2016. Lecture Notes in Computer Science(), vol 9648. Springer, Cham. https://doi.org/10.1007/978-3-319-32034-2_48
Download citation
DOI: https://doi.org/10.1007/978-3-319-32034-2_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-32033-5
Online ISBN: 978-3-319-32034-2
eBook Packages: Computer ScienceComputer Science (R0)