{"id":"W3172135703","doi":"10.1109/jsac.2021.3087250","title":"Radio Frequency Fingerprint Identification for LoRa Using Deep Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Wireless Signal Modulation Classification","field":"Computer Science","cited_by":259,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"National Key Research and Development Program of China; Royal Society","keywords":"Computer science; Deep learning; Spectrogram; Artificial intelligence; Universal Software Radio Peripheral; Carrier frequency offset; Multilayer perceptron; Convolutional neural network; Wireless; Time–frequency analysis; Artificial neural network; Pattern recognition (psychology); Speech recognition; Machine learning; Frequency offset; Orthogonal frequency-division multiplexing; Filter (signal processing); Telecommunications; Computer vision; Channel (broadcasting)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000837694,0.0001654963,0.0002171013,0.0004164249,0.0008160211,0.0004913497,0.00159611,0.0001153712,0.00001123502],"category_scores_gemma":[0.00102231,0.0001886574,0.0001017934,0.001718441,0.00005522806,0.0007305514,0.0001108661,0.0008292033,0.0000178898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006230915,"about_ca_system_score_gemma":0.0004599071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001201644,"about_ca_topic_score_gemma":0.00007501426,"domain_scores_codex":[0.9974775,0.0007334846,0.0007905037,0.0003515666,0.0003487921,0.0002981682],"domain_scores_gemma":[0.9955597,0.0008714285,0.000585444,0.001437878,0.001429229,0.000116307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003562019,0.001292944,0.01179243,0.00004176339,0.0001513507,0.00002554146,0.003295552,0.2036216,0.5355557,0.1596638,0.0002041454,0.08431946],"study_design_scores_gemma":[0.000617754,0.0000576163,0.03851494,0.0001711376,0.00002116254,0.0002210151,0.0001059778,0.9317336,0.01314392,0.0141216,0.0009810525,0.000310202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07305456,0.0004837961,0.9221595,0.003295854,0.0004043895,0.0002425675,0.000002351161,0.0001139065,0.0002430653],"genre_scores_gemma":[0.8680654,0.0002589545,0.1313223,0.00009401681,0.0001033757,0.00004953585,0.00002956514,0.00002150527,0.00005530389],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7950109,"threshold_uncertainty_score":0.7693228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06964920209736099,"score_gpt":0.3229304058749288,"score_spread":0.2532812037775678,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}