Open AccessApplication of Artificial Neural Network(ANN) and Feature Selection Algorithm(FSA) on the ATLAS Experiment Data to Identify Higgs Boson
Author(s) -
Haozhan Tang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1873/1/012072
Subject(s) - large hadron collider , higgs boson , upgrade , atlas (anatomy) , atlas experiment , artificial neural network , particle physics , physics , computer science , atlas detector , artificial intelligence , nuclear physics , machine learning , paleontology , biology , operating system
From the 1950s, physicists started to smash particles together to temporarily form new smaller particles for observing and studying. With further development and enormous experiments, physicists had successfully built the Large Hadron Collider, which became the key hardware for proton colliding. The historical research and experiment in this field have provided us a number of referring data from the LHC experiment and the detailed information of the LHC upgrade to LH-LHC during the previous several years. The Higgs Boson detected by ATLAS Detector in 2013 was significant to scientific research, and its associated dataset could form a new hypothesis to predict the universe rule for small particles. In this study, both Artificial Neural Network(ANN) and Feature Selection Algorithm(FSA) are applied to the ATLAS experiment data to identify Higgs Boson, including the characteristics and fitness for the current model of nature. The study is based on the experiment result of head-on collisions of protons of extraordinarily high energy. The study is aimed to explore the potential of both methods of ANN and FSA to improve the significance of the experiment study and discovery. It will benefit further study to develop the full potential and the enormous scope of physics opportunities given by LHC.