{"id":"W4390873725","doi":"10.1109/tcomm.2024.3354204","title":"RL-Based Hyperparameter Selection for Spectrum Sensing With CNNs","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Distributed Sensor Networks and Detection Algorithms","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Hyperparameter; Computer science; Convolutional neural network; Selection (genetic algorithm); Artificial intelligence; Reinforcement learning; Cognitive radio; Detector; Hyperparameter optimization; Machine learning; Artificial neural network; Channel (broadcasting); Pattern recognition (psychology); Wireless","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":[0.0001572521,0.0001705993,0.000137946,0.0002640727,0.0007044689,0.0004437375,0.000554081,0.00008154051,0.00001747545],"category_scores_gemma":[0.000003178995,0.0001552073,0.0001448054,0.001098441,0.00008721706,0.0003145609,0.000003447972,0.0003812476,0.00005027427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001283112,"about_ca_system_score_gemma":0.0001289968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004484922,"about_ca_topic_score_gemma":0.0002888262,"domain_scores_codex":[0.9989064,0.00008583067,0.0002168426,0.0003584459,0.0001729633,0.0002594931],"domain_scores_gemma":[0.9980473,0.0005499372,0.00004072272,0.001163793,0.0001093035,0.00008893337],"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":[0.0001256122,0.0008178078,0.000004304911,0.00007916308,0.0004265689,0.000007373912,0.0004827386,0.4189727,0.001816839,0.01886718,0.002955848,0.5554438],"study_design_scores_gemma":[0.0002599237,0.0002456876,0.000006672367,0.00006436945,0.00004521768,0.00004947084,0.00001785672,0.9601009,0.008258047,0.0008755142,0.02987716,0.0001991722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000229844,0.00009066888,0.9915916,0.005526338,0.0005797104,0.0003553263,0.00004341821,0.0009035382,0.0006795999],"genre_scores_gemma":[0.8053125,0.00003661702,0.1938393,0.0002511628,0.00003967497,0.00008045855,0.00001114274,0.00002530206,0.0004037557],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8050827,"threshold_uncertainty_score":0.632917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02687445469216907,"score_gpt":0.2662217112580339,"score_spread":0.2393472565658648,"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."}}