{"id":"W4413968650","doi":"10.1016/j.mlwa.2025.100728","title":"CNN-CCA: A deep learning approach for anomaly detection in metro rail sensor time-series data","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Anomaly detection; Deep learning; Anomaly (physics); Series (stratigraphy); Computer science; Time series; Artificial intelligence; Real-time computing; Data mining; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005223784,0.0002231917,0.0002569389,0.0003885634,0.0007597764,0.0001998281,0.001059877,0.0001076956,0.000009036352],"category_scores_gemma":[0.00008955638,0.0002123932,0.00005594919,0.001797321,0.00007403336,0.0004341231,0.0003679995,0.0004334984,0.00002351249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008826696,"about_ca_system_score_gemma":0.00006204237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001457237,"about_ca_topic_score_gemma":0.0001348608,"domain_scores_codex":[0.9981916,0.0001068037,0.0003467901,0.0008765782,0.0001555388,0.000322679],"domain_scores_gemma":[0.9983522,0.0001760051,0.0002004143,0.001081204,0.0001239807,0.00006613823],"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":[0.0002374533,0.0008524904,0.03700677,0.0003133791,0.0002344525,0.000002645418,0.0005853997,0.06455748,0.01510885,0.06887348,0.0003444217,0.8118832],"study_design_scores_gemma":[0.0004731217,0.0001562665,0.002138162,0.00001323298,0.00003449099,0.000009877417,0.0001177032,0.8669712,0.00276576,0.0006217928,0.1264115,0.0002869059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001183453,0.0001648239,0.9932464,0.0006602677,0.00001241194,0.001290618,0.000009506359,0.0008563997,0.00257617],"genre_scores_gemma":[0.540187,0.00002533497,0.4521842,0.00009395918,0.00004883184,0.003323133,0.0002205596,0.00002926557,0.003887712],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8115963,"threshold_uncertainty_score":0.8661143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01102660145688371,"score_gpt":0.2546715695148593,"score_spread":0.2436449680579756,"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."}}