{"id":"W3007670733","doi":"10.3390/s20051261","title":"Designing a Streaming Algorithm for Outlier Detection in Data Mining—An Incrementa Approach","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data stream mining; Sliding window protocol; Anomaly detection; Streaming data; Outlier; Data mining; Context (archaeology); Streaming algorithm; Concept drift; Scalability; Big data; Algorithm; Database; Artificial intelligence; Window (computing)","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":[0.0002382122,0.00009476017,0.0001046879,0.00007236259,0.0001219395,0.00008701751,0.0006270742,0.00005131216,0.000001571833],"category_scores_gemma":[0.00002704075,0.0001006009,0.00002350535,0.0003759043,0.00001585925,0.0003388141,0.0001999502,0.00008803011,0.000003408285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003081569,"about_ca_system_score_gemma":0.00001735197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005513297,"about_ca_topic_score_gemma":0.00001444065,"domain_scores_codex":[0.998982,0.00004208387,0.0001861808,0.0005085026,0.0001067596,0.0001745084],"domain_scores_gemma":[0.999291,0.00003756135,0.00006981772,0.0004955879,0.00002780179,0.00007824881],"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":[0.00000483144,0.00005779896,0.00006967371,0.00001030892,0.000008612204,0.000001490062,0.001111443,0.0003347149,0.007364892,0.0002340671,0.0001311918,0.990671],"study_design_scores_gemma":[0.0001772598,0.00008638266,0.00008556604,0.00000374402,0.00000456779,0.000004373251,0.0005458342,0.9738771,0.02254093,0.00007512679,0.002476114,0.0001230256],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01544641,0.000007564463,0.9834572,0.0002017136,0.00002497498,0.0003734156,0.00001197057,0.0002710385,0.0002057045],"genre_scores_gemma":[0.3532071,0.000001980458,0.6464679,0.0001465854,0.00006659888,0.00005782199,0.00001842065,0.000009431486,0.00002418896],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.990548,"threshold_uncertainty_score":0.4102384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07941839438265871,"score_gpt":0.2957602859902442,"score_spread":0.2163418916075855,"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."}}