{"id":"W4388514100","doi":"10.18280/ria.370525","title":"Utilising Deep Convolutional Neural Networks for Classifying Fire Disasters Through Surveillance: An Indoor and Outdoor Perspective to Predict Man-Made or Natural Disaster","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Convolutional neural network; Natural disaster; Computer science; Artificial intelligence; Geography; Meteorology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002655817,0.0002660176,0.0003048403,0.00009493023,0.0002899396,0.0001322097,0.0001885353,0.0001274838,0.00003497769],"category_scores_gemma":[0.0001507489,0.0002434715,0.0001038816,0.000563098,0.0001110927,0.0003345834,0.00006253258,0.0002551585,0.00004664616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001564439,"about_ca_system_score_gemma":0.00001236687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003834542,"about_ca_topic_score_gemma":0.000231647,"domain_scores_codex":[0.9983125,0.00006166392,0.0004419558,0.0004778975,0.0001636283,0.0005424051],"domain_scores_gemma":[0.9990909,0.0003180075,0.00005265965,0.0002780315,0.0001052199,0.0001551822],"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":[0.0003007745,0.00003108168,0.001255865,0.0002205054,0.00007495745,0.0000156735,0.01584908,0.9567,0.0010994,0.0005063914,0.001066464,0.0228798],"study_design_scores_gemma":[0.0001101165,0.0001382354,0.001194941,0.00008260623,0.000009480702,0.00003968837,0.02011279,0.9759274,0.0003795559,0.0000848185,0.001615283,0.0003051423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6848444,0.0007935556,0.307102,0.0009678166,0.003684842,0.001281964,0.00008243458,0.0008887603,0.0003541695],"genre_scores_gemma":[0.9981049,0.00005122615,0.0003146428,0.0001212498,0.0004291874,0.0001139839,0.00004458336,0.00006002863,0.0007602333],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3132604,"threshold_uncertainty_score":0.9928479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0406861484312016,"score_gpt":0.2860225309425158,"score_spread":0.2453363825113142,"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."}}