{"id":"W3200397134","doi":"10.1145/3460976","title":"Extending Isolation Forest for Anomaly Detection in Big Data via K-Means","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Cyber-Physical Systems","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Big data; SPARK (programming language); Intrusion detection system; Isolation (microbiology); Streaming data; Data mining; Anomaly (physics); Artificial intelligence; Real-time 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002050005,0.001484675,0.001714191,0.002994527,0.001546369,0.001191723,0.002573922,0.001334904,0.0008439812],"category_scores_gemma":[0.006970271,0.0006621009,0.002098059,0.002918145,0.000813722,0.002729979,0.001243043,0.002449878,0.0009044614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008138237,"about_ca_system_score_gemma":0.001812397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01716638,"about_ca_topic_score_gemma":0.02645513,"domain_scores_codex":[0.9986325,0.0002665924,0.0001026774,0.0004642431,0.0003624346,0.0001716455],"domain_scores_gemma":[0.9964651,0.001620671,0.0002948446,0.0006084515,0.0008553214,0.0001556976],"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":[0.0004318772,0.0006114751,0.01380405,0.0002291357,0.000412892,0.0002285997,0.000274396,0.5445089,0.005347387,0.00369192,0.00978356,0.4206758],"study_design_scores_gemma":[0.000007892517,0.00001591646,0.0004749083,0.000004426815,0.00000992828,0.00002783133,0.00001518099,0.9937363,0.0007011231,0.004494226,0.0005037797,0.000008430105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0275718,0.0004823418,0.9644151,0.0003317529,0.0001252345,0.0001003303,0.0004892437,0.005837886,0.0006462719],"genre_scores_gemma":[0.4318206,0.0003884715,0.5623704,0.0003545161,0.0002482863,0.0002244473,0.002879256,0.0004185984,0.001295369],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01716638,"threshold_uncertainty_score":0.0341329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04601198017966552,"score_gpt":0.2710519071490929,"score_spread":0.2250399269694274,"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."}}