{"id":"W3164441817","doi":"10.1002/cjce.24202","title":"Neural network identification of water pipe blockage from smart embedded passive acoustic measurements","year":2021,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Water Systems and Optimization","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Representation (politics); Fourier transform; Computer science; Acoustics; Set (abstract data type); Amplitude; Data set; Identification (biology); Flow (mathematics); Process (computing); Artificial intelligence; Mathematics; Physics; Mechanics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001555943,0.0001054504,0.000187866,0.00004902487,0.00003145402,0.00005232684,0.0001640225,0.0000663281,0.00003893889],"category_scores_gemma":[0.0000590142,0.00007854027,0.00007201701,0.0001133512,0.00001489669,0.00008823352,0.000009119862,0.000190657,0.000002219364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001209302,"about_ca_system_score_gemma":0.00005811379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001887373,"about_ca_topic_score_gemma":0.0006344819,"domain_scores_codex":[0.9990906,0.00001602999,0.0004330618,0.0000646351,0.0001674037,0.0002282926],"domain_scores_gemma":[0.9994153,0.00002666314,0.00006430135,0.0001491603,0.0001737118,0.0001708923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001202034,0.000001203002,0.00006064758,0.00001814782,0.00005404881,0.00001278411,0.0002327825,0.639019,0.360233,0.000001955962,0.000330863,0.00003437731],"study_design_scores_gemma":[0.0001875741,0.000004318616,0.0002398164,0.00009664783,0.0000615581,0.00003572392,0.00001428772,0.2235329,0.7755619,0.00003296313,0.0001284693,0.0001038884],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802023,0.000626062,0.01748201,0.0001352345,0.001394416,0.00006723196,0.00001172594,0.00002089914,0.00006014193],"genre_scores_gemma":[0.9993206,0.000001729315,0.0002502124,0.00001280733,0.0003495759,0.000001834543,0.00001382859,0.00002466082,0.00002478874],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4154861,"threshold_uncertainty_score":0.320278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009972029192553173,"score_gpt":0.1684395932514346,"score_spread":0.1584675640588815,"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."}}