{"id":"W2791180278","doi":"10.1145/3018896.3018950","title":"Subspace selection in high-dimensional big data using genetic algorithm in apache spark","year":2017,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Linear subspace; Outlier; Subspace topology; Computer science; Data mining; Curse of dimensionality; Data point; Anomaly detection; Clustering high-dimensional data; SPARK (programming language); Population; Scale (ratio); Selection (genetic algorithm); Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Cluster analysis","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":[0.0002316223,0.00008341788,0.00009674841,0.0001370966,0.0002120765,0.0001577298,0.0009890835,0.0000614486,0.000009640302],"category_scores_gemma":[0.00001575996,0.00008167695,0.00001378985,0.0002672549,0.00003393148,0.0003973084,0.0005529347,0.0001247731,0.0000129112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006455028,"about_ca_system_score_gemma":0.00006358215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004287499,"about_ca_topic_score_gemma":0.001221792,"domain_scores_codex":[0.9990869,0.00002774352,0.0001644061,0.0004173806,0.0001296517,0.000173886],"domain_scores_gemma":[0.9989048,0.00001673513,0.00009118952,0.0009170496,0.00003006365,0.00004021627],"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":[0.000005167743,0.0002644148,0.02728387,0.000008038049,0.00001033965,0.00002029013,0.00007469756,0.002435624,0.01053883,0.009142156,0.001167157,0.9490494],"study_design_scores_gemma":[0.0001604042,0.00001633483,0.1281184,0.000009196904,0.000001589777,0.00002147091,0.000003226685,0.865331,0.004026134,0.00156047,0.0006349328,0.0001168244],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1006662,0.00001695208,0.8982863,0.0005044381,0.00009195961,0.000138437,0.00000231628,0.0000887854,0.0002046057],"genre_scores_gemma":[0.5586249,0.000006689007,0.4411184,0.00004987212,0.00005570976,0.000009904498,0.000001815111,0.000004226589,0.0001283908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9489326,"threshold_uncertainty_score":0.6481445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08433379621789451,"score_gpt":0.307438046025988,"score_spread":0.2231042498080935,"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."}}