{
  "annotation_id": "91e356fe-995c-472f-b9d9-44b547f7fea2",
  "date_created": "2026-03-02T18:01:21.742000Z",
  "date_modified": "2026-03-02T18:01:21.742000Z",
  "file_hash": "2d5e2911724eabe7a682f7940b0309f831a2619c81206f64dafc4eb54dbb5cbc",
  "private": false,
  "record": {
    "abstract": "A Feed Forward Error Back Propagation Artificial Neural Network(ANN)\nalgorithm is developed for electron/positron identification in a wide momentum\nregion (10 - 300 GeV/c). The method was proposed for the Transition Radiation\nDetector of the E781 experiment at Fermilab. The package consists of two parts:\n  - the program for the ANN training;\n  - the particle classification subroutine.\n  Both parts are built using the object oriented technique and C++ language.\nThe particle identification algorithm is wrapped in FORTRAN closers to be used\nin the E781 off-line program. The package performance was tested in comparison\nwith the likelihood ratio method using Monte Carlo generated data. Our study\nhas demonstrated the excellent ability of the ANN to learn even small details\nof the detector response function. The ANN solution gives the same performance\nand behavior as the likelihood method when using Monte Carlo data with known\ndetector parameters. It demonstrates that if trained with experimental data the\npackage can provide a very good solution to the classification problem of\n$e^+/e^-$ tracks.",
    "arxiv_id": "physics/9811039",
    "authors": [
      "N. Kuropatkin",
      "R. Zukanovich Funchal"
    ],
    "categories": [
      "physics.comp-ph",
      "physics.data-an"
    ],
    "title": "The Network Solution For Electron Identification in a Wide Momentum   Region with a TRD",
    "url": "https://arxiv.org/abs/physics/9811039"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "afd94a59-92c7-4705-af11-1ee914d2c1cb",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}