{"id":"W3093926104","doi":"10.1145/3467981","title":"A Federated Learning Approach to Anomaly Detection in Smart Buildings","year":2021,"lang":"en","type":"preprint","venue":"ACM Transactions on Internet of Things","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Baseline (sea); Task (project management); Internet of Things; Machine learning; Convergence (economics); Building automation; Efficient energy use; Artificial intelligence; Federated learning; Computer security; Systems engineering; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003718944,0.0003177562,0.0004268621,0.0007153555,0.000144872,0.0003686331,0.001351593,0.0003712849,0.00002380012],"category_scores_gemma":[0.0000615731,0.0003630685,0.0002637404,0.0008919024,0.00004144329,0.0003765083,0.000248004,0.001490752,0.00001161081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002439779,"about_ca_system_score_gemma":0.00008616196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002872562,"about_ca_topic_score_gemma":0.0000968637,"domain_scores_codex":[0.9977168,0.0001175362,0.0006169208,0.0009672226,0.0003063811,0.0002751525],"domain_scores_gemma":[0.9985146,0.00008078772,0.0002766798,0.0008162903,0.0002051662,0.00010651],"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":[0.000179273,0.0022535,0.0002452501,0.0006012543,0.0004008653,0.00001800982,0.0182968,0.04886647,0.04107764,0.0018594,0.000175557,0.886026],"study_design_scores_gemma":[0.000483218,0.0006260665,0.0008395658,0.0008380826,0.00005801547,0.00008081522,0.000607856,0.3852025,0.6053608,0.001953443,0.00289447,0.001055192],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1146281,0.00002141065,0.882641,0.0004054601,0.0002492793,0.0004596369,0.000001836567,0.0004285809,0.001164725],"genre_scores_gemma":[0.8132674,0.00002175186,0.1854613,0.0002271331,0.00001298967,0.0002916811,0.000006419515,0.00002650993,0.0006847538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8849708,"threshold_uncertainty_score":0.9998821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01795899356818903,"score_gpt":0.2524868078945012,"score_spread":0.2345278143263121,"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."}}