{"id":"W2177453126","doi":"10.1109/pacrim.2015.7334883","title":"Multi-class acoustic event classification of hydrophone data","year":2015,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; University of Victoria","funders":"","keywords":"Hydrophone; Computer science; Hidden Markov model; Mel-frequency cepstrum; Pattern recognition (psychology); Classifier (UML); Speech recognition; Artificial intelligence; Feature extraction; Artificial neural network; Statistical classification; Acoustics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001503993,0.0007391488,0.001155153,0.002065099,0.0004550607,0.000897977,0.001126232,0.001132432,0.0009104472],"category_scores_gemma":[0.004768809,0.0001930929,0.0006007284,0.001067737,0.0003983327,0.001367969,0.0009244045,0.0009588914,0.000759304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003142599,"about_ca_system_score_gemma":0.000381709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001482878,"about_ca_topic_score_gemma":0.001891494,"domain_scores_codex":[0.9982283,0.000321736,0.0001647081,0.0003963789,0.0006981863,0.0001907945],"domain_scores_gemma":[0.9962897,0.001551248,0.0003983682,0.0006977136,0.0008922522,0.0001706727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005916575,0.0003443065,0.02362492,0.0002289286,0.0001269347,0.0003779459,0.0003183238,0.025884,0.06446331,0.001065947,0.002025028,0.8809487],"study_design_scores_gemma":[0.00002428669,0.0002227891,0.04503204,0.00003902257,0.0000801809,0.0005187382,0.0003655916,0.9030747,0.04373319,0.003208284,0.003608538,0.00009258508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2632431,0.0007677705,0.7319295,0.0002590865,0.0001926425,0.0001546658,0.00047507,0.001138883,0.001839189],"genre_scores_gemma":[0.8148431,0.0003133721,0.1810194,0.0001143683,0.0001589411,0.0001328088,0.001117726,0.00009502543,0.002205303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002065099,"threshold_uncertainty_score":0.007953942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1666482928083657,"score_gpt":0.3319139407615773,"score_spread":0.1652656479532116,"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."}}