{"id":"W4411172260","doi":"10.1109/jiot.2025.3578445","title":"Bayesian Optimization-Aided Hybrid Deep Learning Model for Lightweight UAV-Based Smoke Detection","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; CARE Canada","funders":"University of Southern Mississippi","keywords":"Computer science; Bayesian optimization; Artificial intelligence; Smoke; Bayesian probability; Deep learning; Machine learning; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005192774,0.0007875676,0.000735034,0.0003628958,0.0002246527,0.0006023911,0.001268868,0.0007851278,0.001566614],"category_scores_gemma":[0.001129868,0.0004095933,0.0005632672,0.0003475036,0.0003805312,0.000687116,0.0008767701,0.001191981,0.0003750726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007188377,"about_ca_system_score_gemma":0.001150674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01110669,"about_ca_topic_score_gemma":0.01433766,"domain_scores_codex":[0.9997929,0.00003514043,0.00001033151,0.00005184136,0.00006570446,0.00004412855],"domain_scores_gemma":[0.9997328,0.0001116953,0.0000312898,0.00001646569,0.00008792153,0.00001972273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009349892,0.00006820171,0.0009376493,0.00004813596,0.0000427775,0.0000498668,0.00002715188,0.9125825,0.003347336,0.003300598,0.001506999,0.07799531],"study_design_scores_gemma":[0.000001623494,0.000004587154,0.00003397292,0.000001395743,0.000002147038,0.000002628806,9.344716e-7,0.9992993,0.0001874803,0.0003953104,0.0000692601,0.000001285723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01779785,0.0003312461,0.9791796,0.0001866961,0.00003640617,0.00002571277,0.00008046755,0.0006939056,0.001668243],"genre_scores_gemma":[0.8196684,0.0004601188,0.1727362,0.0004062912,0.00006299544,0.0001756777,0.0004693194,0.0001282315,0.005892731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01110669,"threshold_uncertainty_score":0.02208412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008159244840038323,"score_gpt":0.2179412923359096,"score_spread":0.2097820474958712,"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."}}