{"id":"W4389485261","doi":"10.1007/s00170-023-12713-2","title":"Incremental learning of LSTM-autoencoder anomaly detection in three-axis CNC machines","year":2023,"lang":"en","type":"article","venue":"The International Journal of Advanced Manufacturing Technology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Anomaly detection; Artificial intelligence; Computer science; Machine learning; Process (computing); Artificial neural network; Transfer of learning; Anomaly (physics)","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":[0.0003706368,0.00009932279,0.000155909,0.0008661443,0.00007696355,0.00002708427,0.001393073,0.00007120484,0.00000922892],"category_scores_gemma":[0.0000712622,0.0000776136,0.00007824615,0.0004592949,0.00007720025,0.0003008768,0.0003904016,0.0004091047,0.000006999014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001064799,"about_ca_system_score_gemma":0.0000253431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004699446,"about_ca_topic_score_gemma":0.00007600699,"domain_scores_codex":[0.9989431,0.00002284311,0.0004438241,0.0001512072,0.0002906093,0.0001484081],"domain_scores_gemma":[0.9990891,0.00007644972,0.0004657217,0.0002166189,0.0001328381,0.00001926409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007839723,0.00007716793,0.003095757,0.000009275001,0.00009071265,0.00004697356,0.0001905366,0.02441569,0.2219286,0.01246472,0.00003638934,0.7375658],"study_design_scores_gemma":[0.0003911405,0.0001931455,0.01785722,0.00004397473,0.000004729116,0.0002321494,0.0001277755,0.02193424,0.891879,0.06560848,0.001626654,0.0001014928],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7071917,0.00003765116,0.2900144,0.002195463,0.000240347,0.0000744417,7.535106e-7,0.0001643109,0.00008090235],"genre_scores_gemma":[0.9842097,0.0001265649,0.01551408,0.00003562968,0.00004302626,0.00001501164,4.800382e-7,0.000008277747,0.00004729069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7374642,"threshold_uncertainty_score":0.3164991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00942708967161831,"score_gpt":0.26356812604379,"score_spread":0.2541410363721717,"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."}}