Department of Physics

Permanent URI for this communityhttps://hdl.handle.net/10294/14886

Browse

Browsing Department of Physics by Subject "DBScan."

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Thumbnail Image
    ItemOpen Access
    A novel multi-purpose variational clustering architecture applied to neutron ID within the GlueX BCAL
    (Faculty of Science, University of Regina, 2021-04-21) Giroux, James
    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.