Speaker
연주 김
(서울시립대학교)
Description
The ME0 detector, based on Gas Electron Multiplier (GEM) technology, is a forthcoming component of the Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider, designed to extend muon detection into the very-forward pseudorapidity region of 2.0 < |η| < 2.8. This region faces significant challenges due to high pileup rates, which complicate accurate muon reconstruction. This study investigates the use of deep learning techniques to improve local muon reconstruction within the ME0 detector. By applying advanced neural network models, we aim to enhance reconstruction accuracy and efficiency in the face of high background particle rates, ultimately advancing the detector's performance in this demanding environment.
