{"id":"W3208995432","doi":"10.3390/electronics10212675","title":"A Semantic Segmentation Method for Early Forest Fire Smoke Based on Concentration Weighting","year":2021,"lang":"en","type":"article","venue":"Electronics","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Energy, Northern Development and Mines","funders":"National Natural Science Foundation of China","keywords":"Smoke; Weighting; Segmentation; Pixel; Computer science; Artificial intelligence; Fire detection; Ambiguity; Pattern recognition (psychology); Image segmentation; Environmental science; 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":[0.0001589116,0.0001007062,0.0001131728,0.00002202329,0.00008559211,0.00004450741,0.00003719248,0.00006785258,0.00001497454],"category_scores_gemma":[0.00003495513,0.0001106821,0.00006664368,0.0001503898,0.000003311055,0.00006239824,0.000001821704,0.0001131288,0.000007644204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001808931,"about_ca_system_score_gemma":0.00005602238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006767269,"about_ca_topic_score_gemma":0.0001187974,"domain_scores_codex":[0.9992793,0.00004419372,0.0001765199,0.0001439597,0.0001182786,0.0002377859],"domain_scores_gemma":[0.9996412,0.0001191907,0.00003175699,0.0001212261,0.00005350419,0.00003307331],"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":[0.0001621968,0.0001170827,0.002272655,0.0007693543,0.0002350871,0.00002233765,0.001302812,0.5744514,0.1507155,0.004313049,0.002066672,0.2635719],"study_design_scores_gemma":[0.0005424867,0.0001111443,0.0007820401,0.00002953728,0.00001609022,0.000005525668,0.00003062754,0.9090657,0.08254328,0.0001092003,0.006646125,0.0001182508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2241435,0.0009843407,0.7719377,0.0002465085,0.0006818784,0.0004299768,0.000009752284,0.0003164198,0.00124999],"genre_scores_gemma":[0.9951929,0.000038906,0.004252063,0.0001230858,0.0001089862,0.00006686309,0.00007250597,0.00002502213,0.0001196999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7710494,"threshold_uncertainty_score":0.4513485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01010927841231603,"score_gpt":0.2451593727692901,"score_spread":0.2350500943569741,"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."}}