{"id":"W4238230534","doi":"10.32920/ryerson.14652645.v1","title":"Cloud data segmentation and classification for reverse engineering using neural networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Surface Roughness and Optical Measurements","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Point cloud; Artificial intelligence; Segmentation; Computer science; Feature (linguistics); Pattern recognition (psychology); Computer vision; Artificial neural network; Feature vector; Principal curvature; Gaussian curvature; Curvature; Normal; Surface (topology); Mathematics; Mean curvature; Geometry","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":[0.0004683839,0.0009218085,0.0008661135,0.002247787,0.0005816203,0.001089257,0.001079281,0.001181099,0.002141879],"category_scores_gemma":[0.001291277,0.0005887945,0.00117714,0.002000993,0.0003944222,0.001151588,0.0006960747,0.000802649,0.001043052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00137768,"about_ca_system_score_gemma":0.0008081764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01576507,"about_ca_topic_score_gemma":0.01710071,"domain_scores_codex":[0.9996305,0.0000346385,0.00002880588,0.00012782,0.0001143788,0.00006380256],"domain_scores_gemma":[0.9995741,0.0001243319,0.00006372423,0.00005518423,0.0001639585,0.00001860097],"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":[0.0002176949,0.0001316212,0.002444182,0.00009857881,0.00007056433,0.00011124,0.00006047314,0.3228942,0.01489441,0.002213817,0.002993817,0.6538695],"study_design_scores_gemma":[0.000002232182,0.000009043001,0.0003550803,0.000005057212,0.000004566088,0.00001017957,0.000008647692,0.9962708,0.00207832,0.0008502213,0.0004018722,0.000003999412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03207265,0.0004484946,0.9625288,0.0001753949,0.00005926337,0.0001225205,0.0002812364,0.00297786,0.001333677],"genre_scores_gemma":[0.418304,0.000567412,0.5741633,0.000142835,0.00008948331,0.0002934406,0.00139821,0.0002232807,0.004817969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01576507,"threshold_uncertainty_score":0.03134662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1291375355187871,"score_gpt":0.295886930688503,"score_spread":0.1667493951697159,"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."}}