{"id":"W2991440093","doi":"10.1109/smc.2019.8914029","title":"Visual fingerprinting for lobsters using deep learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Exoskeleton; Deep learning; Fishery; Human–computer interaction; Machine learning; Biology; Simulation","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":[0.0003355079,0.000522556,0.0003524593,0.0009877308,0.0002389091,0.0006783126,0.0005735258,0.0006066317,0.002174987],"category_scores_gemma":[0.0007418349,0.0002344039,0.0003882119,0.0004867414,0.0002342519,0.0005560346,0.0007492461,0.0005412681,0.001327055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000515788,"about_ca_system_score_gemma":0.0004947157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009420048,"about_ca_topic_score_gemma":0.01439188,"domain_scores_codex":[0.9998566,0.00001309891,0.000006129859,0.0000499561,0.00002599002,0.0000482788],"domain_scores_gemma":[0.9998114,0.00004187774,0.00003113702,0.00003525447,0.00005544065,0.00002502225],"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":[0.0003819188,0.000160487,0.0311175,0.0001223709,0.0001546483,0.0003275209,0.0001341767,0.07606976,0.05441902,0.002081151,0.004651031,0.8303804],"study_design_scores_gemma":[0.00001396132,0.0001178319,0.01833153,0.000074702,0.00004693463,0.0003740769,0.0001219054,0.9457253,0.02722539,0.003014454,0.004921841,0.00003205209],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4579002,0.002644963,0.5199056,0.0003742309,0.0001775065,0.000109003,0.002098126,0.006417375,0.010373],"genre_scores_gemma":[0.8842844,0.0005387978,0.1033802,0.000150575,0.00002905744,0.00004504949,0.001653656,0.0001085394,0.009809684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009420048,"threshold_uncertainty_score":0.0187304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01809534940651012,"score_gpt":0.3035841517338741,"score_spread":0.285488802327364,"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."}}