Speaker
Description
Clusters counting in a drift chamber represents a highly promising
breakthrough in particle identification (PID) techniques for particle physics
experiments. In this paper, we trained neural network models, including a
Long Short-Term Memory (LSTM) model for the peak-finding algorithm and a
Convolutional Neural Network (CNN) model for the clusterization algorithm,
using various hyperparameters such as loss functions, activation functions,
numbers of neurons, batch sizes, and different numbers of epochs. These
models were trained utilizing high-performance computing (HPC) resources
provided by the ReCas computing center. The best LSTM peak-finding model
was selected based on the highest area under the curve (AUC) value, while
the best CNN clusterization model was chosen based on the lowest mean
square error (MSE) value among all configurations. The training was
conducted on momentum ranges from 0.2 to 20 GeV.
The trained models (LSTM and CNN) were subsequently tested on samples
with momenta of 4 GeV/c, 6 GeV/c, 8 GeV/c, and 10 GeV/c. The simulation
parameters included 10% Helium (He) and 90% Isobutane (C4H10), a cell
size of 0.8 cm, a sampling rate of 2 GHz, a time window of 800 ns, 5000
events, and a 45-degree angle between the muon particle track and the z-axis
(sense wire) of the drift tube chamber. The testing aimed to evaluate the
performance of the LSTM model for peak finding and the CNN model for
clusterization.
