{"id":"W4402901213","doi":"10.3390/modelling5040069","title":"Novel Adaptive Hidden Markov Model Utilizing Expectation–Maximization Algorithm for Advanced Pipeline Leak Detection","year":2024,"lang":"en","type":"article","venue":"Modelling—International Open Access Journal of Modelling in Engineering Science","topic":"Water Systems and Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Leak detection; Pipeline (software); Expectation–maximization algorithm; Leak; Maximization; Markov chain; Hidden Markov model; Algorithm; Forward algorithm; Markov model; Machine learning; Artificial intelligence; Maximum likelihood; Variable-order Markov model; Mathematical optimization; Engineering; Mathematics; Statistics; Programming language","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":[0.001069249,0.0007026677,0.001174002,0.0005297993,0.0003635882,0.0007817775,0.001379434,0.001019304,0.001933718],"category_scores_gemma":[0.002305382,0.0005301799,0.001117047,0.0005830926,0.0003898476,0.001151727,0.0007676314,0.001470362,0.0005902289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005204451,"about_ca_system_score_gemma":0.001242639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009290615,"about_ca_topic_score_gemma":0.007184514,"domain_scores_codex":[0.9994844,0.0001537934,0.00003379481,0.0001280646,0.0001221702,0.00007773479],"domain_scores_gemma":[0.9990301,0.000665487,0.00008036002,0.00002993396,0.0001583544,0.00003571648],"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":[0.0002517902,0.0001513053,0.003398877,0.0001628347,0.0001476703,0.0002547984,0.0001210272,0.8134625,0.006080748,0.01119855,0.002730163,0.1620398],"study_design_scores_gemma":[0.000003014941,0.000007826025,0.00006427015,0.00000202502,0.000003666708,0.00001236383,0.000002247205,0.9987277,0.0002131001,0.0008458608,0.0001145513,0.000003295909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008874884,0.0003236762,0.9894708,0.0001457776,0.00004094416,0.00001817245,0.00004560479,0.0004306521,0.0006494357],"genre_scores_gemma":[0.6337731,0.0007696117,0.3590225,0.0002954393,0.0001239705,0.0001807053,0.0005089109,0.0001575713,0.005168186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009290615,"threshold_uncertainty_score":0.01847303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05123299499623737,"score_gpt":0.3072032868765379,"score_spread":0.2559702918803006,"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."}}