May 16, 2023 Master Thesis Open Access

Dorwarth, Philipp Benjamin

JSON Export

{
  "conceptrecid": "22195", 
  "created": "2023-10-10T04:57:07.265084+00:00", 
  "files": [
    {
      "bucket": "a28ca8fc-da2c-47da-a214-f8c50f1b80be", 
      "checksum": "md5:0c176e7016bd1923a6968b3f509219fb", 
      "key": "Masterthesis.pdf", 
      "links": {
        "self": "https://publish.etp.kit.edu/api/files/a28ca8fc-da2c-47da-a214-f8c50f1b80be/Masterthesis.pdf"
      }, 
      "size": 32087364, 
      "type": "pdf"
    }
  ], 
  "id": 22197, 
  "links": {
    "bucket": "https://publish.etp.kit.edu/api/files/a28ca8fc-da2c-47da-a214-f8c50f1b80be", 
    "html": "https://publish.etp.kit.edu/record/22197", 
    "latest": "https://publish.etp.kit.edu/api/records/22197", 
    "latest_html": "https://publish.etp.kit.edu/record/22197"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "belle2"
      }, 
      {
        "id": "etp"
      }
    ], 
    "contributors": [], 
    "creators": [
      {
        "affiliation": "KIT/ETP", 
        "name": "Dorwarth, Philipp Benjamin"
      }
    ], 
    "description": "<p>This thesis investigates components of a Graph Neural Network (GNN)-based pipeline addressing challenges of current tracking algorithms at the Belle II experiment, such as highly displaced vertices and escalating beam backgrounds. The thesis examines input features for real-time pattern recognition algorithms, systematic graph-building in the Central Drift Chamber (CDC), which serves as the primary tracking detector, and the use of the Interaction Network (IN) for edge classification and background clean-up.</p>\n\n<p>The study finds that Analog-to-Digital Converter (ADC) count and Time-to-Digital Converter (TDC) count, representing deposited energy and associated timing information in a CDC cell, provide orthogonal discrimination power, making them both valuable for distinguishing signal from background.</p>\n\n<p>Different patterns for graph-building in the CDC are analyzed to find graphs that effectively encapsulate crucial information about signal particle tracks of a simulated Inelastic Dark Matter with a Dark Higgs model. Metrics are introduced to aid in balancing between capturing essential edges connecting signal hits and excluding those associated with background.</p>\n\n<p>The graphs are evaluated, employing the IN as a classifier for graph edges. This process allows for the identification of signal hits and the execution of a background clean-up. The clean-up task&nbsp;yields&nbsp;a promising result, correctly identifying&nbsp;up to (80.6 &plusmn; 0.4) % of signal hits in the CDC while maintaining a purity of (67.4 &plusmn; 0.4) % in the hit selection. An initial analysis towards a real-time implementation is also conducted, aligning&nbsp;the input feature resolution with the anticipated resolutions at the Level 1 Trigger (L1 Trigger) stage.</p>\n\n<p>This thesis provides encouraging evidence that a GNN-based pipeline offers a viable solution to the challenges posed.</p>", 
    "keywords": [
      "Belle II", 
      "Graph Neural Network", 
      "Deep Learning", 
      "Graph-Building", 
      "Pattern Recognition", 
      "Central Drift Chamber", 
      "Displaced Vertices"
    ], 
    "language": "eng", 
    "publication_date": "2023-05-16", 
    "relations": {
      "version": [
        {
          "count": 2, 
          "index": 1, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "22197"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "22195"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "master-thesis", 
      "title": "Master Thesis", 
      "type": "thesis"
    }, 
    "thesis": {
      "report_number": "ETP-KA/2023-07", 
      "supervisors": [
        {
          "affiliation": "KIT/ETP", 
          "name": "Ferber, Torben"
        }, 
        {
          "affiliation": "KIT/ETP", 
          "name": "Klute, Markus"
        }
      ]
    }, 
    "title": "Graph-Building and Input Feature Analysis for Edge Classification in the Central Drift Chamber at Belle II"
  }, 
  "owners": [
    92
  ], 
  "revision": 1, 
  "stats": {}, 
  "updated": "2023-10-10T04:57:07.481213+00:00"
}