{"id":"W3159387031","doi":"10.3390/app9163245","title":"Intelligent Identification of Maceral Components of Coal Based on Image Segmentation and Classification","year":2019,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"China Postdoctoral Science Foundation","keywords":"Maceral; Liptinite; Inertinite; Computer science; Artificial intelligence; Vitrinite; Pattern recognition (psychology); Segmentation; Coal; Identification (biology); Cluster analysis; Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000764899,0.00077008,0.0005446678,0.003735571,0.0003762023,0.001001826,0.000759232,0.0007472535,0.001247799],"category_scores_gemma":[0.00104421,0.0003223126,0.0006733403,0.001027952,0.0005390718,0.0009097726,0.0006458699,0.0003973476,0.0008932784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003737199,"about_ca_system_score_gemma":0.0006280967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002501002,"about_ca_topic_score_gemma":0.00466763,"domain_scores_codex":[0.9995957,0.00003027288,0.00002451853,0.0001342074,0.000143932,0.00007137201],"domain_scores_gemma":[0.9994169,0.0001272898,0.00009749078,0.00007911302,0.0002426614,0.000036577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003356222,0.00009576452,0.01382852,0.0004518938,0.00007465079,0.0002916279,0.000427835,0.01313968,0.3568353,0.002244605,0.003113676,0.6091608],"study_design_scores_gemma":[0.00002518219,0.0001465593,0.03441185,0.00007652785,0.000141712,0.0008388673,0.0004428018,0.6258425,0.3238678,0.004605317,0.009519124,0.00008170561],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1241859,0.0005417845,0.8659341,0.0001722813,0.00004990037,0.0002045328,0.0003818015,0.004998139,0.003531387],"genre_scores_gemma":[0.317199,0.0005340187,0.6785021,0.0001284469,0.00004113631,0.0001108641,0.000809059,0.0003677491,0.00230751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003735571,"threshold_uncertainty_score":0.004972935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02857254850750418,"score_gpt":0.2668554731084631,"score_spread":0.238282924600959,"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."}}