{"id":"W4283740537","doi":"10.1038/s41598-022-15272-w","title":"A lightweight YOLOv3 algorithm used for safety helmet detection","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Key Technology Research and Development Program of Shandong; Qilu University of Technology; Natural Science Foundation of Shandong Province","keywords":"Computer science; Backbone network; Algorithm; Residual; Object detection; Network model; Artificial intelligence; Feature (linguistics); Point (geometry); Data mining; Pattern recognition (psychology); Computer network; Mathematics","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":[0.0005988745,0.001144781,0.0008788669,0.001677223,0.0007274013,0.0008456728,0.001721717,0.001022583,0.005959261],"category_scores_gemma":[0.001821343,0.0005021491,0.0008750824,0.0009531326,0.0004588163,0.001582343,0.001378712,0.0008851826,0.002358051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009584757,"about_ca_system_score_gemma":0.001614925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01055545,"about_ca_topic_score_gemma":0.01681455,"domain_scores_codex":[0.9995841,0.00003857685,0.00002176935,0.0001721436,0.000110844,0.0000725499],"domain_scores_gemma":[0.9996368,0.00006196806,0.00004002638,0.00006598687,0.000163647,0.00003164035],"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":[0.0006231025,0.0001284843,0.006323849,0.0002612813,0.0001326169,0.0001523638,0.0001155902,0.0930067,0.03241195,0.006406916,0.02494791,0.8354893],"study_design_scores_gemma":[0.00006590662,0.0001454732,0.002205379,0.00004041359,0.00004235429,0.0001931413,0.00007027697,0.9579762,0.02332962,0.003920165,0.01197821,0.00003285451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04171545,0.000668812,0.9405046,0.0002515191,0.0002450358,0.0002489192,0.001080747,0.01023882,0.005046117],"genre_scores_gemma":[0.2902352,0.0004760907,0.6878651,0.0004679963,0.0001011715,0.0003538869,0.006007002,0.001200928,0.01329267],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01055545,"threshold_uncertainty_score":0.02098799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01453191031547135,"score_gpt":0.2557249312197714,"score_spread":0.2411930209043,"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."}}