Speaker
Description
Particle identification (PID) is crucial for future particle physics experiments like CEPC and FCC-ee. A promising breakthrough in PID involves cluster counting, which quantifies primary ionizations along a particle’s trajectory in a drift chamber (DC), bypassing the need for dE/dx measurements. However, a major challenge lies in developing an efficient reconstruction algorithm to recover cluster signals from DC cell waveforms.
In PID, machine learning algorithms have emerged as the state-of-the-art. For simulated samples, a supervised model based on LSTM and DGCNN achieves a remarkable 10% improvement in separating K from $\pi$ compared to traditional methods. For test beam data samples collected at CERN, due to label scarcity and data/MC discrepancy, a semi-supervised domain adaptation model is developed and validated using pseudo data. When applied to real data, this model outperforms traditional methods and maintains consistent performance across varying track lengths.
| I read the instructions above | Yes |
|---|
