{"id":"W2588557298","doi":"10.1109/ssci.2016.7850074","title":"Feature extraction and target classification of side-scan sonar images","year":2016,"lang":"en","type":"article","venue":"","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"Defence Science and Technology Group; Defence Research and Development Canada","keywords":"Side-scan sonar; Sonar; Computer science; Feature extraction; Support vector machine; Artificial intelligence; Underwater; Kernel (algebra); Margin (machine learning); Pattern recognition (psychology); Contextual image classification; Feature (linguistics); Data mining; Machine learning; Image (mathematics); Geology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001569777,0.00004950736,0.0000606281,0.0000592934,0.00004388926,0.00002304632,0.00006404454,0.00004445663,0.001398781],"category_scores_gemma":[0.00002289241,0.00002771052,0.00001227591,0.00006336656,0.00008537913,0.0002176138,0.000005227576,0.00004891542,0.00006214227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003227012,"about_ca_system_score_gemma":0.00002503848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003040259,"about_ca_topic_score_gemma":0.0004463257,"domain_scores_codex":[0.9994566,0.00003309687,0.00006778586,0.0001337635,0.0001785536,0.0001302055],"domain_scores_gemma":[0.9996408,0.0001308729,0.000030692,0.00008602499,0.0000483491,0.00006331816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004226565,0.00001347617,0.4234352,0.00002580827,0.00001227743,0.000003545413,0.00004702455,0.0001046007,0.2809826,0.00004518013,0.007209078,0.288079],"study_design_scores_gemma":[0.0001539173,0.0000704649,0.9515753,0.000009006226,0.000003921535,0.00001085037,0.00008424193,0.009216626,0.03197974,0.001318429,0.005506486,0.0000710264],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5586854,0.0007023923,0.3311805,0.01900775,0.0002344946,0.0004879018,0.000359575,0.0001242328,0.08921776],"genre_scores_gemma":[0.9811797,0.0001217245,0.01307077,0.00001548544,0.0000340984,3.54817e-7,0.00001696959,0.000001589709,0.005559344],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5281401,"threshold_uncertainty_score":0.9995141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02457565458334967,"score_gpt":0.2656335170707171,"score_spread":0.2410578624873675,"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."}}