{"id":"W4288085024","doi":"10.1007/s11356-022-22167-w","title":"Applying a deep residual network coupling with transfer learning for recyclable waste sorting","year":2022,"lang":"en","type":"article","venue":"Environmental Science and Pollution Research","topic":"Municipal Solid Waste Management","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Sorting; Transfer of learning; Residual neural network; Computer science; Residual; Artificial intelligence; Deep learning; sort; Machine learning; Algorithm; Database","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006459588,0.0001414764,0.000129847,0.0001174957,0.005642732,0.0001283361,0.0004734496,0.0000272809,0.0011892],"category_scores_gemma":[0.00004270523,0.0001321613,0.00002605582,0.0009963741,0.001221682,0.000358479,0.001209659,0.0005139721,0.00003346241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009516292,"about_ca_system_score_gemma":0.00003199296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002439178,"about_ca_topic_score_gemma":0.00006622783,"domain_scores_codex":[0.9958081,0.0001438545,0.0002204991,0.0006706723,0.002073292,0.001083569],"domain_scores_gemma":[0.9994254,0.00008757357,0.0000458745,0.0002315035,0.000005798046,0.0002038545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001055577,0.00004916809,0.007308555,0.000007176667,0.000005980541,0.000004481073,0.0007095712,0.9714749,0.01126846,0.000289126,0.0002540666,0.008522951],"study_design_scores_gemma":[0.001303409,0.001321212,0.006935216,0.00002590814,0.0000229527,0.00002440817,0.02507656,0.8705143,0.002000098,0.0005268976,0.09169521,0.0005538066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913921,0.00012473,0.001741654,0.0005889248,0.00005825313,0.001637939,0.000004977594,0.00002781376,0.004423614],"genre_scores_gemma":[0.9967042,0.00004198596,0.0006229305,0.0001632518,0.00007148218,0.0009216229,0.000007502955,0.0000208273,0.00144615],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1009606,"threshold_uncertainty_score":0.9997239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03324349108848757,"score_gpt":0.2885636854811574,"score_spread":0.2553201943926698,"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."}}