{"id":"W2985544876","doi":"10.1007/s00773-019-00685-6","title":"Sea bottom line tracking in side-scan sonar image through the combination of points density clustering and chains seeking","year":2019,"lang":"en","type":"article","venue":"Journal of Marine Science and Technology","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"Young Scientists Fund","keywords":"Side-scan sonar; Sonar; Scan line; Cluster analysis; Smoothing; Computer vision; Computer science; Artificial intelligence; Line (geometry); Tracking (education); Synthetic aperture sonar; Geology; Image (mathematics); Mathematics; Geometry","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":[0.001657575,0.00006264535,0.0001631591,0.0004089588,0.0001141222,0.00005935537,0.0003001906,0.0000507529,0.00002708468],"category_scores_gemma":[0.0001912732,0.00004158604,0.00001219518,0.0006963599,0.0006145143,0.0004642487,0.0001806609,0.0003532954,0.000001376793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001439081,"about_ca_system_score_gemma":0.0001118632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005336787,"about_ca_topic_score_gemma":0.00139726,"domain_scores_codex":[0.9989918,0.00003168495,0.000241136,0.000134266,0.0003776127,0.0002234782],"domain_scores_gemma":[0.9993462,0.0001109612,0.0001591422,0.0001007234,0.0002473049,0.00003568601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002459706,0.00001777965,0.8809155,0.00002852257,0.00000508684,0.00002916516,0.0002824164,0.0003004101,0.01432743,0.0001121072,0.000002548138,0.1039545],"study_design_scores_gemma":[0.0007187654,0.0005713227,0.6948059,0.00006825152,0.000007901766,0.0005722588,0.00114938,0.2764673,0.007849962,0.0176492,0.00004376574,0.0000960257],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941217,0.0000556162,0.002009534,0.003109241,0.0000617292,0.0000911851,0.000001349861,0.00000521816,0.0005444704],"genre_scores_gemma":[0.9940096,0.0001487803,0.005767053,0.00004196442,0.00001300723,8.810584e-8,4.686495e-7,0.000001518134,0.00001758206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2761669,"threshold_uncertainty_score":0.2264204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0154993559971572,"score_gpt":0.2614422502657959,"score_spread":0.2459428942686387,"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."}}