{"id":"W3152187070","doi":"10.3390/s21144805","title":"OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection","year":2021,"lang":"en","type":"preprint","venue":"Sensors","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Anomaly detection; Deep learning; Latency (audio); Computer science; Software deployment; Low latency (capital markets); Artificial intelligence; Convolutional neural network; Real-time computing; Computer network; Telecommunications; Software engineering","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":[0.0003682472,0.0006620731,0.0002308043,0.0002883479,0.0001534997,0.0003930641,0.001071215,0.0003717584,0.002050065],"category_scores_gemma":[0.001114179,0.0002306234,0.0002253551,0.0002351771,0.0002623113,0.001154576,0.0005486474,0.0007620484,0.0005577615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004889295,"about_ca_system_score_gemma":0.0005099006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002042238,"about_ca_topic_score_gemma":0.006339042,"domain_scores_codex":[0.9998199,0.00002836304,0.000008057913,0.00003820911,0.00006948545,0.00003591441],"domain_scores_gemma":[0.9996843,0.0001018075,0.00004026866,0.00005154799,0.0001025306,0.00001956016],"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":[0.0006450087,0.0002714576,0.006849702,0.0002898145,0.0001671237,0.0004184289,0.0001358788,0.4919781,0.07710724,0.01537493,0.02044567,0.3863165],"study_design_scores_gemma":[0.00001657473,0.0001723065,0.0007032048,0.00001087887,0.00001691989,0.00007425177,0.00002065053,0.971697,0.01981307,0.003641581,0.003823577,0.00001002894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2081056,0.0007990082,0.7726889,0.0005304475,0.0001895941,0.0001143055,0.0007202409,0.009640978,0.007210935],"genre_scores_gemma":[0.8386311,0.0003017821,0.1535207,0.0002343021,0.00003302241,0.0001112723,0.001107506,0.0002419117,0.005818541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002050065,"threshold_uncertainty_score":0.00685817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01895605087259754,"score_gpt":0.2706947675523367,"score_spread":0.2517387166797392,"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."}}