{"id":"W4405926818","doi":"10.1080/07373937.2024.2445769","title":"A Two-pass deep learning system for monitoring visual attributes of food in real-time during fluidized bed drying","year":2024,"lang":"en","type":"article","venue":"Drying Technology","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Tertiary Education Trust Fund","keywords":"Fluidized bed; Artificial intelligence; Process engineering; Environmental science; Computer science; Engineering; Waste management","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002444265,0.000261001,0.0006366018,0.001087877,0.0001593763,0.0000493407,0.00034349,0.0003907784,0.00003487915],"category_scores_gemma":[0.000402338,0.0002831162,0.0001676445,0.001593669,0.0000802356,0.0001013764,0.000187194,0.0005018422,0.00001163978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004200181,"about_ca_system_score_gemma":0.0000428181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004607175,"about_ca_topic_score_gemma":0.000003109068,"domain_scores_codex":[0.9981149,0.00001892373,0.0005708777,0.0005323852,0.0001796024,0.0005832803],"domain_scores_gemma":[0.9990481,0.0003864266,0.0001646036,0.0002780845,0.00007795799,0.00004487797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004651344,0.00003416881,0.01676195,0.001285439,0.0002231298,0.00003638918,0.0001526543,0.00005716457,0.9797843,0.0006880566,0.000001098364,0.0009291584],"study_design_scores_gemma":[0.0009471106,0.00007676897,0.00004730897,0.0006148466,0.0001534074,0.00003036698,0.002210975,0.003272267,0.9921833,0.000199753,0.00001657267,0.0002473617],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939655,0.003426886,0.0004557403,0.00005186474,0.0001031304,0.0001251928,0.00000874027,0.001502806,0.0003601578],"genre_scores_gemma":[0.9978651,0.00009462849,0.00156803,5.130175e-7,0.0001459469,0.0001485521,0.00001485383,0.00006631178,0.00009603649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01671464,"threshold_uncertainty_score":0.9999621,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01415748933890243,"score_gpt":0.2944918008389786,"score_spread":0.2803343115000761,"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."}}