BM@N Tracking with Novel Deep Learning Methods
| Autor: | Dmitriy Baranov, Pavel Goncharov, Gennady Ososkov, Egor Shchavelev |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
010308 nuclear & particles physics
business.industry Deep learning Physics QC1-999 Detector Pattern recognition Kalman filter Tracking (particle physics) 01 natural sciences Tree (data structure) Recurrent neural network 0103 physical sciences Graph (abstract data type) Artificial intelligence Data pre-processing 010306 general physics business |
| Zdroj: | EPJ Web of Conferences, Vol 226, p 03009 (2020) |
| Popis: | Three deep tracking methods are presented for the BM@N experiment GEM track detector, which differ in their concepts. The first is a two-stage method with data preprocessing by a directional search in the k-d tree to find all possible candidates for tracks, and then use a deep recurrent neural network to classify them by true and ghost tracks. The second end-to-end method used a deep recurrent neural network to extrapolate the initial tracks, similar to the Kalman filter, which learns necessary parameters from the data. The third method implements our new attempt to adapt the neural graph network approach developed in the HEP.TrkX project at CERN to GEM-specific data. The results of applying these three methods to simulated events are presented. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|