{"id":"W4282933099","doi":"10.1109/sustech53338.2022.9794235","title":"Automated Identification of Used Beverage Cans for Deposit Return using Deep Learning Methods","year":2022,"lang":"en","type":"article","venue":"","topic":"Recycling and Waste Management Techniques","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"University of Guelph","keywords":"Sorting; Computer science; Scrap; Identification (biology); Process (computing); Artificial intelligence; Artificial neural network; Convolutional neural network; Deep learning; Work (physics); Engineering; Algorithm; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001040894,0.00006588814,0.00009949777,0.00004970437,0.0002743914,0.0000217314,0.0001778027,0.00002131861,0.0003063575],"category_scores_gemma":[0.00004035753,0.00006702083,0.00004994899,0.000232185,0.00002767425,0.00008992666,0.0001968875,0.0000759035,0.000001559977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001491609,"about_ca_system_score_gemma":0.000002293419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009337036,"about_ca_topic_score_gemma":0.00003458564,"domain_scores_codex":[0.9990601,0.000186554,0.0002486788,0.0001971338,0.0001784414,0.0001290681],"domain_scores_gemma":[0.9996006,0.00006465192,0.0001547752,0.0001537503,0.000005151026,0.00002099548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001405107,0.00005473334,0.04515535,0.00002583754,0.00002227615,0.000001015441,0.0007144531,0.1431519,0.7806753,0.00008627921,0.0004276285,0.02967114],"study_design_scores_gemma":[0.0001113152,0.00005540759,0.008338246,0.000002955789,0.0000223574,0.00000187693,0.0003452,0.8629931,0.1266091,0.000209931,0.001213347,0.0000971346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4765869,0.000007447191,0.521746,0.00002223041,0.00005096238,0.0002411014,0.000001213098,0.0002938963,0.00105027],"genre_scores_gemma":[0.8618509,0.000002275919,0.1368437,0.00002608918,0.000004345918,0.00004085594,0.00001053136,0.00001164613,0.00120966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7198411,"threshold_uncertainty_score":0.33544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02605477443573181,"score_gpt":0.3318621048105789,"score_spread":0.3058073303748471,"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."}}