Dataset Open Access

AN OPEN-SOURCED TIME-FREQUENCY DOMAIN RF CLASSIFICATION FRAMEWORK

Badger, Robert; Kim, Minje


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.4603987", 
  "language": "eng", 
  "title": "AN OPEN-SOURCED TIME-FREQUENCY DOMAIN RF CLASSIFICATION FRAMEWORK", 
  "issued": {
    "date-parts": [
      [
        2021, 
        3, 
        14
      ]
    ]
  }, 
  "abstract": "<p>These datasets accompany the EUSIPCO 2021 paper:&nbsp;AN OPEN-SOURCED TIME-FREQUENCY<br>\nDOMAIN RF CLASSIFICATION FRAMEWORK</p>\n\n<p>Labeled in-phase and quadrature (IQ)&nbsp;datasets captured using software defined radios (SDR).&nbsp;12 classes comprised of 10 different transceivers plus &#39;noise&#39; class and class for zero hz artifact from SDR direct conversion receiver.</p>\n\n<p>The IQ data has the extension .sigmf-data, and the associated JSON file that contains the labeled metadata is .sigmf-meta.</p>\n\n<p>There is a directory called &#39;data&#39;, this has all the extracted features for each class and is used for training.</p>\n\n<p>There are also 12 folders named &#39;data_val1&#39; - &#39;data_val12&#39;. These contain the extracted features used validation accuracy.</p>\n\n<p>There are numerous training, validation and testing datasets used to build the training and validation sets, all comprised of the ten primary RF modulation waveforms:</p>\n\n<p>1) LoRa 125 (lora125)</p>\n\n<p>2) LoRa 250 (lora250)</p>\n\n<p>3) PTT analog transceivers (uv5r, vx8)</p>\n\n<p>4) PTT digital transceivers (gd55, tyt)</p>\n\n<p>5) RF doorbell (vod, sado)</p>\n\n<p>6) misc. RF keyfob (click)</p>\n\n<p>7) RF light switch (light)</p>\n\n<p>8) Yaesu system fusion PTT (ysf)</p>\n\n<p>The testing directory:&nbsp;testing_data_1msps conatins all the test data for the auto grader notebooks at the github repo.</p>\n\n<p>These datasets go with the public github repo called:&nbsp;https://github.com/rdbadger/open_source_RFML</p>\n\n<p>&nbsp;</p>", 
  "author": [
    {
      "family": "Badger, Robert"
    }, 
    {
      "family": "Kim, Minje"
    }
  ], 
  "id": "4603987", 
  "event-place": "Dublin, Ireland", 
  "type": "dataset", 
  "event": "29th European Signal Processing Conference (EUSIPCO)"
}
87
1
views
downloads
All versions This version
Views 8787
Downloads 11
Data volume 183.5 GB183.5 GB
Unique views 7171
Unique downloads 11

Share

Cite as