1 Ocak 2021 Konferans bildirisi Açık Erişim

Kaya, Engin; Kaplan, Gulay Buyukaksoy

JSON

{
  "conceptrecid": "240069", 
  "created": "2022-10-07T10:45:35.657546+00:00", 
  "doi": "10.1109/RadarConf2147009.2021.9455167", 
  "files": [
    {
      "bucket": "f3706729-1202-4316-90f9-5a37e99e6508", 
      "checksum": "md5:a9d6f3866c08bd9e445097adbd93944d", 
      "key": "bib-955f9093-cecc-492b-950a-b10bb016c1a5.txt", 
      "links": {
        "self": "https://aperta.ulakbim.gov.tr/api/files/f3706729-1202-4316-90f9-5a37e99e6508/bib-955f9093-cecc-492b-950a-b10bb016c1a5.txt"
      }, 
      "size": 171, 
      "type": "txt"
    }
  ], 
  "id": 240070, 
  "links": {
    "badge": "https://aperta.ulakbim.gov.tr/badge/doi/10.1109/RadarConf2147009.2021.9455167.svg", 
    "bucket": "https://aperta.ulakbim.gov.tr/api/files/f3706729-1202-4316-90f9-5a37e99e6508", 
    "doi": "https://doi.org/10.1109/RadarConf2147009.2021.9455167", 
    "html": "https://aperta.ulakbim.gov.tr/record/240070", 
    "latest": "https://aperta.ulakbim.gov.tr/api/records/240070", 
    "latest_html": "https://aperta.ulakbim.gov.tr/record/240070"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "tubitak-adresli-yayinlar"
      }
    ], 
    "creators": [
      {
        "affiliation": "TUBITAK BILGEM, Informat Technol Inst, TR-41400 Kocaeli, Turkey", 
        "name": "Kaya, Engin"
      }, 
      {
        "affiliation": "TUBITAK BILGEM, Informat Technol Inst, TR-41400 Kocaeli, Turkey", 
        "name": "Kaplan, Gulay Buyukaksoy"
      }
    ], 
    "description": "Increasing drone accidents and abuse has led to the development of drone detection systems. In this study we proposed two classification approaches for the recognition of flying drones using non-coherent S-band radar. The radar data including drone, ship and bird targets is collected in various scenarios. While both of the proposed classification methods utilize neural networks, the first one is trained with the features extracted from track information. The second technique is based on radar images, meaning that video classification methods are employed. The results were investigated with respect to the correct classification performance and false alarm rate. Experimental results have shown that the image based method is better at recognizing not only drone but also birds and ships with a lower false alarm rate.", 
    "doi": "10.1109/RadarConf2147009.2021.9455167", 
    "has_grant": false, 
    "license": {
      "id": "cc-by"
    }, 
    "meeting": {
      "title": "2021 IEEE RADAR CONFERENCE (RADARCONF21): RADAR ON THE MOVE"
    }, 
    "publication_date": "2021-01-01", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "240070"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "240069"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "conferencepaper", 
      "title": "Konferans bildirisi", 
      "type": "publication"
    }, 
    "science_branches": [
      "Di\u011fer"
    ], 
    "title": "Neural Network Based Drone Recognition Techniques With Non-Coherent S-Band Radar"
  }, 
  "owners": [
    1
  ], 
  "revision": 1, 
  "stats": {
    "downloads": 4.0, 
    "unique_downloads": 4.0, 
    "unique_views": 8.0, 
    "version_downloads": 4.0, 
    "version_unique_downloads": 4.0, 
    "version_unique_views": 8.0, 
    "version_views": 8.0, 
    "version_volume": 684.0, 
    "views": 8.0, 
    "volume": 684.0
  }, 
  "updated": "2022-10-07T10:45:35.715159+00:00"
}