Importance-based signal detection and parameter estimation with applications to new particle search
Importance-based signal detection and parameter estimation with applications to new particle search
One of the hardest challenges in data analysis is perhaps the detection of rare anomalous data buried ina huge normal background. We study this problem by constructing a novel method, which is a combination of theKullback–Leibler importance estimation procedure based anomaly detection algorithm and linear discriminant classifier.We choose to illustrate it with the example of charged Higgs boson (CHB) search in particle physics. Indeed, the LargeHadron Collider experiments at CERN ensure that CHB signal must be a tiny effect within the irreducible W-bosonbackground. In simulations, different CHB events with different characteristics are produced and judiciously mixed withthe non-CHB data, and the proposed method is applied. Our results show that distribution parameters of weak CHBsignals can be estimated with high performance. This anomaly detection method is general enough to apply to similarproblems in other fields (e.g., astrophysical, medical, engineering problems).
___
- [1] Tanabashi M, Hagiwara K, Hikasa K, Nakamura K, Sumino Y et al. Review of particle physics. Physical Review D
2018; D98 (1): 030001. doi: 10.1103/PhysRevD.98.030001
- [2] Bhat PC. Multivariate analysis methods in particle physics. Annual Review of Nuclear and Particle Science 2011;
61: 281-309. doi: 10.1146/annurev.nucl.012809.104427
- [3] Carli T, Koblitz B. A multi-variate discrimination technique based on range-searching. Nuclear Instruments and
Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 2003;
501 (2-3): 576-588. doi: 10.1016/S0168-9002(03)00376-0
- [4] Wolter M. Multivariate analysis methods in physics. Physics of Particles and Nuclei 2007; 38 (2): 255-268. doi:
10.1134/S1063779607020050
- [5] Chandola V, Banerjee A, Kumar V. Anomaly detection: a survey. ACM Computing Surveys (CSUR) 2009; 41 (3):
15:1-15:58. doi: 10.1145/1541880.1541882
- [6] Aleskerov E, Freisleben B, Rao B. Cardwatch: a neural network based database mining system for credit card fraud
detection. In: IEEE/IAFE 1997 Computational Intelligence for Financial Engineering (CIFEr); New York City,
NY, USA; 1997. pp. 220-226.
- [7] Mohiuddin A, Mahmood AN, Islam MR. A survey of anomaly detection techniques in financial domain. Future
Generation Computer Systems 2016; 55 (C): 278-288. doi: 10.1016/j.future.2015.01.001
- [8] Kumar V. Parallel and distributed computing for cybersecurity. IEEE Distributed Systems Online 2005; 6 (10):
1-9. doi: 10.1109/MDSO.2005.53
- [9] Liao Z, Kong L, Wang X, Zhao Y, Zhou F et al. A visual analytics approach for detecting and understanding
anomalous resident behaviors in smart healthcare. Applied Sciences 2017; 7 (3): 254. doi: 10.3390/app7030254
- [10] Riveiro M, Lebram M, Elmer M. Anomaly detection for road traffic: a visual analytics framework. IEEE Transactions
on Intelligent Transportation Systems 2017; 18 (8): 2260-2270. doi: 10.1109/TITS.2017.2675710
- [11] Yuan Y, Wang D, Wang Q. Anomaly detection in traffic scenes via spatial-aware motion reconstruction. IEEE
Transactions on Intelligent Transportation Systems 2017; 18 (5): 1198-1209. doi: 10.1109/TITS.2016.2601655
- [12] Breunig MM, Kriegel HP, Ng RT, Sander J. Lof: identifying density-based local outliers. In: ACM SIGMOD
International Conference on Management of Data; Dallas, TX, USA; 2000. pp. 93-104. doi: 10.1145/335191.335388
- [13] Tang J, Chen Z, Fu AWC, Cheung DW. Enhancing effectiveness of outlier detections for low density patterns.
In: Pacific-Asia Conference on Knowledge Discovery and Data Mining; Taipei, Taiwan; 2002. pp. 535-548. doi:
10.1007/3-540-47887-6_53.
- [14] Schölkopf B, Williamson RC, Smola AJ, Shawe-Taylor J, Platt JC. Support vector method for novelty detection.
In: Advances in Neural Information Processing Systems 12; Denver, CO, USA; 1999. pp. 582-588.
- [15] Guedes R, Moretti S, Santos R. Charged higgs bosons in single top production at the LHC. Journal of High Energy
Physics 2012; 10: 119. doi: 10.1007/JHEP10(2012)119
- [16] Vatanen T, Kuusela M, Malmi E, Raiko T, Aaltonen T et al. Semi-supervised detection of collective anomalies with
an application in high energy particle physics. In: The 2012 International Joint Conference on Neural Networks
(IJCNN); Brisbane, QLD, Australia; 2012. pp. 1-8.
- [17] Aissa NB, Guerroumi M. Semi-supervised statistical approach for network anomaly detection. Procedia Computer
Science 2016; 83: 1090-1095. doi: 10.1016/j.procs.2016.04.228
- [18] Sugiyama M, Nakajima S, Kashima H, Buenau PV, Kawanabe M. Direct importance estimation with model selection
and its application to covariate shift adaptation. In: Advances in Neural Information Processing Systems 20;
Vancouver, BC, Canada; 2007. pp. 1-8.
- [19] Sugiyama M, Suzuki T, Nakajima S, Kashima H, Buenau PV et al. Direct importance estimation for covariate shift
adaptation. Annals of The Institute of Statistical Mathematics 2008; 60 (4): 699-746. doi: 10.1007/s10463-008-
0197-x
- [20] Hido S, Tsuboi Y, Hashima H, Sugiyama M, Kanamori T. Statistical outlier detection using direct density ratio
estimation. Knowledge and Information Systems 2011; 26 (2): 309-336. doi: 10.1007/s10115-010-0283-2
- [21] Hull JJ. A database for handwritten text recognition research. IEEE Transactions on Pattern Analysis and Machine
Intelligence 1994; 16 (5): 550-554. doi:10.1109/34.291440
- [22] Branco GC, Ferreira PM, Lavoura L, Rebelo MN, Sher M et al. Theory and phenomenology of two-higgs-doublet
models. Physics Reports 2012; 516 (1-2): 1-102. doi: 10.1016/j.physrep.2012.02.002
- [23] Hashemi M. Observability of light charged higgs decay to muon in top quark pair events at LHC. European Physical
Journal 2012; 72 (5): 1994. doi: 10.1140/epjc/s10052-012-1994-1
- [24] Eriksson D, Rathsman J, Stal O. 2HDMC: Two-higgs-doublet model calculator. Computer Physics Communication
2010; 181 (1): 189-205. doi: 10.1016/j.cpc.2009.09.011
- [25] Alwall J, Artoisenet P, de Visscher S, Duhr C, Frederix M et al. New developments in MadGraph/MadEvent. In:
16th International Conference on Supersymmetry and the Unification of Fundamental Interactions; Seoul, Korea;
2008. pp. 84-89. doi: 10.1063/1.3052056
- [26] Moretti S. 2HDM charged higgs boson searches at the LHC: status and prospects. In: Prospects for Charged Higgs
Discovery at Colliders; Uppsala, Sweden; 2016. doi: 10.22323/1.286.0014
- [27] Webb AR, Copsey KD. Statistical Pattern Recognition. 3rd ed. West Sussex, UK: John Wiley & Sons, 2011.