{"id":"W4410114800","doi":"10.1109/jiot.2025.3567543","title":"Noise-Aware Ensemble Learning for Efficient Radar Modulation Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Wireless Signal Modulation Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"Defense Acquisition Program Administration; Korea Research Institute for Defense Technology Planning and Advancement","keywords":"Computer science; Radar; Noise (video); Speech recognition; Frequency modulation; Artificial intelligence; Pattern recognition (psychology); Telecommunications; Bandwidth (computing)","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":[0.0007198956,0.0001157967,0.0001713967,0.0003415883,0.0001358666,0.0001983127,0.0004757405,0.00008382276,0.000009558464],"category_scores_gemma":[0.0001824831,0.0001151138,0.0001330756,0.000249917,0.00002579803,0.0005592934,0.00004796847,0.0002758062,0.00001026013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001592091,"about_ca_system_score_gemma":0.00008402282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001556082,"about_ca_topic_score_gemma":7.096376e-7,"domain_scores_codex":[0.9986569,0.00009944304,0.0005198144,0.0002415663,0.0003052625,0.0001770061],"domain_scores_gemma":[0.9984621,0.0002057744,0.0005309356,0.0001643639,0.0005835263,0.0000532811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001873858,0.0002506804,0.0007754961,0.0001745193,0.0001433405,0.000004718363,0.003822292,0.1571361,0.3080305,0.009979448,0.003572864,0.5159227],"study_design_scores_gemma":[0.0004698112,0.00008942711,0.001194993,0.0002789494,0.00001309762,0.00002256382,0.00003814547,0.8932078,0.09625056,0.007958135,0.0003721367,0.0001043803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1796874,0.0000260188,0.817924,0.0007297582,0.001086998,0.0001535446,5.141375e-7,0.00005854584,0.0003331699],"genre_scores_gemma":[0.9645035,0.000004584845,0.03470813,0.0001247557,0.00008985175,0.000009792859,0.00000507288,0.00000906784,0.0005452877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.784816,"threshold_uncertainty_score":0.4694206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02849473364446518,"score_gpt":0.2709784127854211,"score_spread":0.2424836791409559,"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."}}