{"id":"W4224236327","doi":"10.3390/min12040455","title":"Deep-Learning-Based Automatic Mineral Grain Segmentation and Recognition","year":2022,"lang":"en","type":"article","venue":"Minerals","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Deep learning; Computer science; Artificial intelligence; Segmentation; Automation; Task (project management); Process (computing); Pattern recognition (psychology); Machine learning; Residual neural network; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004603504,0.0008700623,0.0006812902,0.001216563,0.0003514332,0.0007308866,0.001653737,0.0009350333,0.002558833],"category_scores_gemma":[0.0009010423,0.00044857,0.000654375,0.0008776116,0.000580011,0.001344235,0.0007197401,0.0007916975,0.001858196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028849,"about_ca_system_score_gemma":0.001313066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009065771,"about_ca_topic_score_gemma":0.02031238,"domain_scores_codex":[0.9996554,0.00002362871,0.00001395485,0.0001139638,0.0001323608,0.00006070401],"domain_scores_gemma":[0.9996784,0.00007674716,0.00004533687,0.00006197986,0.0001169194,0.0000207538],"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":[0.0004031247,0.0003237897,0.004825382,0.0002963801,0.0001213635,0.0001527708,0.00008960482,0.2284238,0.1092482,0.005837864,0.01402021,0.6362576],"study_design_scores_gemma":[0.000008545072,0.00002737656,0.00104866,0.000008376032,0.00001271151,0.00003878475,0.00001259423,0.9598514,0.03439508,0.002091365,0.002493795,0.00001135881],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1175964,0.0008945565,0.8534132,0.000387241,0.0001494509,0.0001257158,0.001331224,0.01817582,0.007926423],"genre_scores_gemma":[0.4931979,0.0004547685,0.4931949,0.0003027508,0.00004717135,0.00009812124,0.00337077,0.0003933183,0.008940238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009065771,"threshold_uncertainty_score":0.01802599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01378851185898026,"score_gpt":0.2249850948605009,"score_spread":0.2111965830015206,"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."}}