On the Identification of Quark and Gluon Jets Using Artificial Neural Network Method

ZHANG Kun-Shi; LIU Lian-Shou

Chinese Physics C> 2004, Vol. 28> Issue(11) : 1141-1145

On the Identification of Quark and Gluon Jets Using Artificial Neural Network Method

ZHANG Kun-Shi ,
LIU Lian-Shou ^,

Institute of Particle Physics,Huazhong Normal University,Wuhan 430079,China2 School of Physics Science and Technology,Yangtze University,Jingzhou 434020,China

Abstract
HTML
Reference
Related

PDF

Abstract：
The identification of quark and gluon jets produced in e^＋e^－collisions using the artificial neural network method is addressed.The structure and the learning algorithm of the BP(Back Propagation)neural network model is studied.Three characteristic parameters—the average multiplicity and the average transverse momentum of jets and the average value of the angles opposite to the quark or gluon jets are taken as training parameters and are inputed to the BP network for repeated training.The learning process is ended when the output error of the neural network is less than a pre-set precision(σ=0.005).The same training routine is repeated in each of the 8 energy bins ranging from 2.5—22.5 GeV,respectively.The finally updated weights and thresholds of the BP neural network are tested using the quark and gluon jet samples,getting from the non-symmetric three-jet events produced by the Monte Carlo generator JETSET 7.4.Then the pattern recognition of the mixed sample getting from the combination of the quark and gluon jet samples is carried out through applying the trained BP neural network.It turns out that the purities of the identified quark and gluon jets are around 75%—85%,showing that the artificial neural network is effective and practical in jet analysis.It is hopeful to use the further improved BP neural network to study the experimental data of high energy e^＋e^－ collisions.

References

[1]

. AMY Coll. Kim Y Ket al. Phys. Rev. Lett., 1989, 63: 172. JADE Coll. Bartel W et al. Phys. Lett., 1983, B123: 4603. OPAL Coll. Alexander G et al. Phys. Lett., 1991, B265: 4624. HU Shou-Ren et al. Neural Networks Introduction. Changsha: National University of Defense Technology Publishers, 1993 (in Chinese)(胡守仁等. 神经网络导论. 长沙: 国防科学技术大学出版社, 1993)5. Bishop C M. Neural Networks for Pattern Recognition. Oxford, UK: Oxford University Press, 19956. Ripey B D. Pattern Recognition and Neural Networks. Combridge, UK: Cambridge University Press, 19967. HAN Jia-Wei. Micheline Kamber, Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers, 20028. Dokshitzer YU L. J. Phys., 1991, G17: 15379. ZHANG Kun-Shi, CHEN Gang, YU Mei-Ling et al. HEP NP, 2002, 26(11): 1110 (in Chinese)(张昆实, 陈刚, 喻梅凌等. 高能物理与核物理, 2002, 26(11): 1110)10. YU Mei-Ling, LIU Lian-Shou. Chin. Phys. Lett, 2002, 19: 647

[1]	GUO Yun-Jun , HE Kang-Lin . Muon Identification Using the Efficiencies Ratio Method at BESⅡ. Chinese Physics C, 2007, 31(11): 1050-1055.
[2]	HUANG Wen-Xue , WANG Yue , ZHU Zhi-Chao , TIAN Yu-Lin , XU Hu-Shan , SUN Zhi-Yu , XIAO Guo-Qing , ZHAN Wen-Long . Experimental Study of the High-Voltage Breakdown and Simulations for the RFQ Cooler and Buncher RFQ1L. Chinese Physics C, 2006, 30(S2): 261-264.
[3]	SHEN Shui-Fa , YU Xiao-Han . Decay of ⁸³Sr and Discussion of Its Daughter's Band Structures. Chinese Physics C, 2004, 28(S1): 78-80.
[4]	LI Ming-Liang , ZHU Sheng-Jiang , CHE Xing-Lai , YU Ying-Nan . Research on Two-Quasiparticle Bands in ⁹⁸Sr. Chinese Physics C, 2004, 28(S1): 75-77.
[5]	Guo Hua . In-medium QMC Model Parameters and Quark Condensation in Nuclear Matter. Chinese Physics C, 1999, 23(5): 459-468.
[6]	Yang Jianjun , Ma Boqiang , Li Guanglie . Non-perturbative Quark Propagator and the Study of the Non-trivial Q² Dependence in the Nucleon Structure Functions. Chinese Physics C, 1997, 21(2): 146-156.
[7]	Yu Hong , Shen Qixing , Zhang Lin . Angular Distribution of Process e⁺e^－→τ⁺τ^－,τ^－→a₁υτ,a₁→ρπ and Characteristics of a₁ Meson. Chinese Physics C, 1994, 18(7): 583-590.
[8]	BES Collaboration . Experimental Study of Resonance f₂(1270) in the J/ψ Hadronic Decay. Chinese Physics C, 1993, 17(2): 97-106.
[9]	SANG Jian-Ping , LIU Chao-Shan , LIU Yong . Relation Between the Gap at Z=64 Subshell and the Abrupt Transition in the Region N=88～90. Chinese Physics C, 1991, 15(2): 150-157.
[10]	HOU Ren-Chang , ZHAO Xuan . QUADRUPOLE-OCTUPOLE TWO-PHONON EXCITATIONS IN INELASTIC SCATTERING. Chinese Physics C, 1983, 7(2): 236-244.
[11]	Sa Ben-hao , Zhang Xi-zhen , Li Zhu-xia , Shi Yi-jin . A PRIMARY RESEARCH OF THE PHONON RENORMALIZATION OF NUCLEAR FIELD THEORY. Chinese Physics C, 1980, 4(3): 398-400.

Access

Get Citation

ZHANG Kun-Shi and LIU Lian-Shou. On the Identification of Quark and Gluon Jets Using Artificial Neural Network Method[J]. Chinese Physics C, 2004, 28(11): 1141-1145.

ZHANG Kun-Shi and LIU Lian-Shou. On the Identification of Quark and Gluon Jets Using Artificial Neural Network Method[J]. Chinese Physics C, 2004, 28(11): 1141-1145. shu

RIS(for EndNote,Reference Manager,ProCite)

BibTex

Txt

Milestone

Received: 2004-05-08
Revised: 1900-01-01

Article Metric

Article Views(3424)
PDF Downloads(626)
Cited by(0)

Policy on re-use

To reuse of subscription content published by CPC, the users need to request permission from CPC, unless the content was published under an Open Access license which automatically permits that type of reuse.

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

On the Identification of Quark and Gluon Jets Using Artificial Neural Network Method

ZHANG Kun-Shi
LIU Lian-Shou ^,

Corresponding author: LIU Lian-Shou,

Institute of Particle Physics,Huazhong Normal University,Wuhan 430079,China2 School of Physics Science and Technology,Yangtze University,Jingzhou 434020,China

Received Date: 2004-05-08
Accepted Date: 1900-01-01
Available Online: 2004-11-05

Abstract: The identification of quark and gluon jets produced in e^＋e^－collisions using the artificial neural network method is addressed.The structure and the learning algorithm of the BP(Back Propagation)neural network model is studied.Three characteristic parameters—the average multiplicity and the average transverse momentum of jets and the average value of the angles opposite to the quark or gluon jets are taken as training parameters and are inputed to the BP network for repeated training.The learning process is ended when the output error of the neural network is less than a pre-set precision(σ=0.005).The same training routine is repeated in each of the 8 energy bins ranging from 2.5—22.5 GeV,respectively.The finally updated weights and thresholds of the BP neural network are tested using the quark and gluon jet samples,getting from the non-symmetric three-jet events produced by the Monte Carlo generator JETSET 7.4.Then the pattern recognition of the mixed sample getting from the combination of the quark and gluon jet samples is carried out through applying the trained BP neural network.It turns out that the purities of the identified quark and gluon jets are around 75%—85%,showing that the artificial neural network is effective and practical in jet analysis.It is hopeful to use the further improved BP neural network to study the experimental data of high energy e^＋e^－ collisions.