{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002079828,0.0006950162,0.001141303,0.0009578824,0.0009663188,0.0009633816,0.001534898,0.0007528917,0.0003889175],"category_scores_gemma":[0.003176096,0.0003887745,0.001049021,0.001345006,0.0008371238,0.0008744564,0.001102871,0.0008618429,0.0001458674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001018958,"about_ca_system_score_gemma":0.002282215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01340654,"about_ca_topic_score_gemma":0.008941989,"domain_scores_codex":[0.9990626,0.000270722,0.00005009555,0.000169007,0.0003235703,0.0001239595],"domain_scores_gemma":[0.9988105,0.0005457773,0.00009892378,0.0001207798,0.0003101439,0.0001138537],"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":[0.0001506022,0.0001538201,0.00304068,0.00005855426,0.00008839549,0.0001548177,0.0001929454,0.8976733,0.004708671,0.00443694,0.001595939,0.08774523],"study_design_scores_gemma":[0.00002279121,0.00002033044,0.0002162521,0.000002005639,0.000005085543,0.00001731064,0.00003560078,0.9963438,0.0009207315,0.002129462,0.0002804674,0.00000610491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1139548,0.0002189511,0.8815587,0.0002708181,0.00005174809,0.0001138973,0.00008958032,0.002570392,0.001171209],"genre_scores_gemma":[0.4369799,0.0001258892,0.5614297,0.0001043276,0.00002523536,0.0002315955,0.0002844493,0.0001378666,0.000681183],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01340654,"threshold_uncertainty_score":0.02665704,"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."}}