A novel multi-purpose variational clustering architecture applied to neutron ID within the GlueX BCAL
| dc.contributor.author | Giroux, James | |
| dc.date.accessioned | 2022-05-31T16:24:29Z | |
| dc.date.available | 2022-05-31T16:24:29Z | |
| dc.date.issued | 2021-04-21 | |
| dc.description | A Thesis Submitted in Partial Fulfillment of the Requirements for the Degree of Bachelor of Science (Honours) in Physics, University of Regina. 40 p. | en_US |
| dc.description.abstract | Particle Identification plays a crucial role within the GlueX Barrel Calorimeter. This paper details the implementation of a novel Machine Learning architecture, which combines cutting-edge conditional generative models with clustering algorithms, capable of extracting both e cient and high purity data samples, while only relying on information from only one type of sample. We demonstrate the validity of our approach and highlight its use as a neutron detection device, emphasizing its ability to limit assumptions on background samples. This architecture is flexible and can be extended to multiple categories. Remarkably it can be deployed for a wide range of problems, e.g., anomaly detection and data quality control. | en_US |
| dc.description.authorstatus | Student | en_US |
| dc.description.peerreview | no | en_US |
| dc.identifier.uri | https://hdl.handle.net/10294/14912 | |
| dc.language.iso | en | en_US |
| dc.publisher | Faculty of Science, University of Regina | en_US |
| dc.subject | Electromagnetic calorimeter. | en_US |
| dc.subject | BCAL. | en_US |
| dc.subject | XGBoost. | en_US |
| dc.subject | TensorFlow. | en_US |
| dc.subject | Keras. | en_US |
| dc.subject | HDBSCAN. | en_US |
| dc.subject | DBScan. | en_US |
| dc.subject | Scikit Learn. | en_US |
| dc.subject | Boosted decision tree. | en_US |
| dc.subject | Conditional Sigma Variational Autoencoder. | en_US |
| dc.title | A novel multi-purpose variational clustering architecture applied to neutron ID within the GlueX BCAL | en_US |
| dc.type | Thesis | en_US |