{"id":"W2121741220","doi":"10.1109/pst.2011.5971981","title":"Data preprocessing for distance-based unsupervised Intrusion Detection","year":2011,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Mahalanobis distance; Normalization (sociology); Euclidean distance; Computer science; Pattern recognition (psychology); Intrusion detection system; Artificial intelligence; Preprocessor; Data mining; Outlier; Anomaly detection; Curse of dimensionality; Principal component analysis; Feature extraction; Data pre-processing; Distance measures","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001691212,0.00006924841,0.00006081595,0.00004922213,0.0002107105,0.00006373588,0.0008233471,0.00004096632,0.00002324463],"category_scores_gemma":[0.00001754184,0.00006053764,0.00002569166,0.000249767,0.00002065882,0.0004820159,0.0001654473,0.00004125707,0.000007941065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001903801,"about_ca_system_score_gemma":0.00003164395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002646446,"about_ca_topic_score_gemma":0.00003968805,"domain_scores_codex":[0.9992618,0.00000983529,0.0001417057,0.0003946487,0.00007485633,0.0001171361],"domain_scores_gemma":[0.9988299,0.00002405973,0.00005685598,0.000978899,0.00006975722,0.00004054637],"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":[0.00003639337,0.0001718871,0.0002616115,0.00004465135,0.000007172098,4.060801e-7,0.0001762007,0.00001089704,0.01468442,0.03890339,0.0007456471,0.9449573],"study_design_scores_gemma":[0.0001921919,0.0000800761,0.0004837684,0.000009912699,0.000005030277,0.000001765255,0.0000159127,0.6659109,0.2989934,0.01011665,0.02404903,0.0001412979],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009938685,0.00001276365,0.9957371,0.0001431799,0.0000544744,0.0002800027,0.000008133663,0.0006152673,0.002155242],"genre_scores_gemma":[0.6502904,0.00000163413,0.3493417,0.0001522545,0.00001753234,0.00009474441,0.000007498316,0.000004896794,0.00008937074],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.944816,"threshold_uncertainty_score":0.2468653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1030304552684645,"score_gpt":0.2903539398748656,"score_spread":0.1873234846064011,"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."}}