{"id":"W4303022251","doi":"10.1007/s10696-022-09471-w","title":"Deep learning models for vessel’s ETA prediction: bulk ports perspective","year":2022,"lang":"en","type":"article","venue":"Flexible Services and Manufacturing Journal","topic":"Maritime Ports and Logistics","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Computer science; Leverage (statistics); Automatic Identification System; Arrival time; Port (circuit theory); Deep learning; Convolutional neural network; Artificial intelligence; Operations research; Time of arrival; Artificial neural network; Machine learning; Data mining; Telecommunications; Channel (broadcasting); Engineering; Transport engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0002507575,0.0001634817,0.0001772466,0.0001183885,0.0008091926,0.0001716577,0.0001337808,0.00004510716,0.0004768469],"category_scores_gemma":[0.000002164983,0.0001637006,0.00007099852,0.00004055623,0.0000145267,0.0002473406,0.00009530481,0.0005300139,0.000001013115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001065649,"about_ca_system_score_gemma":0.0000149569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005690518,"about_ca_topic_score_gemma":0.000009137176,"domain_scores_codex":[0.9990569,0.00001877177,0.0002354305,0.000178168,0.0002043365,0.0003063911],"domain_scores_gemma":[0.9996126,0.00003047319,0.00007921104,0.00009673454,0.00004820594,0.0001328045],"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":[0.00002563404,0.00001534047,0.00006697018,0.0001636217,0.00007816948,0.00002619166,0.001324699,0.9918621,0.00001362009,0.0008157245,0.0004022672,0.005205719],"study_design_scores_gemma":[0.0006620961,0.0002067145,0.0009163233,0.00003824416,0.00008830147,0.0007267212,0.00515251,0.8540739,0.0004622805,0.01950391,0.1178425,0.0003264749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4009384,0.02970567,0.4748461,0.001587287,0.009189859,0.001605067,0.0002388334,0.002339863,0.07954897],"genre_scores_gemma":[0.9964433,0.0006847662,0.00118637,0.0001071087,0.0005357026,0.0000307484,0.00002686601,0.00004455018,0.0009405752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5955049,"threshold_uncertainty_score":0.6675516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01493948679344528,"score_gpt":0.2136755450374902,"score_spread":0.1987360582440449,"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."}}