{"id":"W2978858971","doi":"10.1109/iciai.2019.8850815","title":"A Deep Learning Based Forest Fire Detection Approach Using UAV and YOLOv3","year":2019,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":238,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Fire detection; Artificial intelligence; Convolutional neural network; Deep learning; Frame rate; RGB color model; Frame (networking); Convolution (computer science); Artificial neural network; Remote sensing; Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001216507,0.00009876088,0.0001137847,0.0000605887,0.00006453769,0.00003444899,0.00002999636,0.00008607389,0.00004947677],"category_scores_gemma":[0.00001092485,0.00009447658,0.00003359327,0.0001254286,0.000008111202,0.00009084329,0.000008490258,0.0001415297,0.00004240751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000440618,"about_ca_system_score_gemma":0.000003244428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001035209,"about_ca_topic_score_gemma":0.00005604005,"domain_scores_codex":[0.999497,0.00002855718,0.0001209413,0.0001322135,0.00007901292,0.0001422933],"domain_scores_gemma":[0.999802,0.00002675713,0.00001680932,0.00009586223,0.00001429941,0.00004428773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001122448,0.000006534796,0.007841115,0.0001944097,0.00001893352,8.188518e-7,0.0001729828,0.9589143,0.01203938,0.00001490437,0.000006178696,0.0207792],"study_design_scores_gemma":[0.0002607022,0.00002761811,0.003323495,0.00001175057,0.000005024944,0.00002288758,0.0002130832,0.9934198,0.001047693,0.000002262481,0.001540867,0.0001247688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6592406,0.00008985918,0.3340624,0.000003471355,0.0002575686,0.000147838,1.67278e-7,0.0003783242,0.005819709],"genre_scores_gemma":[0.9985133,0.00000364391,0.001047047,0.00001330731,0.00004378888,0.000006574335,0.00000206911,0.00002564226,0.0003445721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3392727,"threshold_uncertainty_score":0.3852643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007592004548448513,"score_gpt":0.1746911730090977,"score_spread":0.1670991684606492,"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."}}