{"id":"W2896715342","doi":"10.1121/1.5067821","title":"Using convolutional neural networks on perceptual and spectral features: Classification experiments on the TREX’13 dataset","year":2018,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Clutter; Timbre; Computer science; Convolutional neural network; Artificial intelligence; Unexploded ordnance; Pattern recognition (psychology); Feature (linguistics); Data set; Set (abstract data type); Range (aeronautics); Acoustics; Backscatter (email); Automatic target recognition; Remote sensing; Geology; Radar; Synthetic aperture radar; Physics; 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":[0.0006223006,0.0001251666,0.0001631181,0.00001762343,0.0005403097,0.00005366911,0.0006035333,0.00005809206,0.0004318967],"category_scores_gemma":[0.0001082804,0.00005309081,0.0001135152,0.0001701489,0.00193568,0.00008044062,0.00005770522,0.0005925692,0.000007969892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002681598,"about_ca_system_score_gemma":0.00006031647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002307601,"about_ca_topic_score_gemma":0.000008169903,"domain_scores_codex":[0.9983124,0.0003326004,0.0002481273,0.0001157907,0.0007057025,0.0002853543],"domain_scores_gemma":[0.9983752,0.0009605086,0.000214731,0.0002576928,0.00009278805,0.00009910383],"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":[0.00197907,0.0002878937,0.005000976,0.00002068905,0.0004456736,0.000003566041,0.003710855,0.7180377,0.01786885,0.000021583,0.2377868,0.01483637],"study_design_scores_gemma":[0.0001962459,0.0005833,0.0305207,0.00002145467,0.00006316994,0.00005341299,0.002194987,0.9657387,0.0001549009,0.000157573,0.0002490039,0.00006661352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7632281,0.0004506727,0.2155225,0.01792395,0.0008887497,0.0005926362,0.0007246947,0.00001568579,0.0006530329],"genre_scores_gemma":[0.9942557,0.0001087748,0.002982645,0.002082518,0.0005229085,1.642473e-7,0.00001538448,0.000004696569,0.00002717241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.247701,"threshold_uncertainty_score":0.7132095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07203946073277029,"score_gpt":0.3138661910471365,"score_spread":0.2418267303143662,"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."}}