{"id":"W4225492836","doi":"10.3390/make4020015","title":"An Attention-Based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Series","year":2022,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Western University","funders":"Government of Canada","keywords":"Autoencoder; Computer science; Artificial intelligence; Thresholding; Anomaly detection; Pattern recognition (psychology); Feature (linguistics); Multivariate statistics; Feature learning; Machine learning; Data mining; Deep learning; Image (mathematics)","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":[0.0004610195,0.0001442165,0.000139053,0.0002612219,0.0009271649,0.0001168761,0.000151542,0.00004930048,0.00003179244],"category_scores_gemma":[0.00001471299,0.0001445765,0.00004177069,0.0004459933,0.00002759013,0.0004720145,0.00004712415,0.0003594715,0.00000414175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001253125,"about_ca_system_score_gemma":0.00004799607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001742533,"about_ca_topic_score_gemma":0.0002373125,"domain_scores_codex":[0.998904,0.0001744123,0.0001980563,0.0004346308,0.0001034114,0.0001854187],"domain_scores_gemma":[0.999491,0.00008806995,0.0001251464,0.000178017,0.00006644244,0.0000512882],"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":[0.0008152677,0.001404783,0.03034537,0.0001609882,0.0000634724,0.00001247743,0.002061719,0.08397781,0.4062802,0.003389916,0.0000261228,0.4714618],"study_design_scores_gemma":[0.0006616719,0.0007025768,0.01430489,0.00001096314,0.00001016606,0.00003330937,0.00009872211,0.9776884,0.001434742,0.0002134036,0.004649152,0.0001920088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1656192,0.00008175683,0.8330122,0.0002263993,0.00007362884,0.0003581297,0.000004776115,0.000451002,0.0001728941],"genre_scores_gemma":[0.976418,0.000004813624,0.0221334,0.00002061949,0.00002325028,0.0004723692,0.00003725708,0.00002125781,0.0008691062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8937106,"threshold_uncertainty_score":0.7131096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006973311791659286,"score_gpt":0.2750364673034,"score_spread":0.2680631555117407,"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."}}