{"id":"W2257550357","doi":"10.1145/2976744","title":"Scalable and Accurate Online Feature Selection for Big Data","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Pairwise comparison; Big data; Computer science; Scalability; Feature (linguistics); Benchmark (surveying); Curse of dimensionality; Selection (genetic algorithm); Artificial intelligence; Data mining; Dimensionality reduction; Set (abstract data type); Machine learning; Pattern recognition (psychology); Database","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":[0.001923,0.001902947,0.00193513,0.002402731,0.001001444,0.001264388,0.002273472,0.00103453,0.001837085],"category_scores_gemma":[0.008684577,0.0006496051,0.001401741,0.003210819,0.0006331607,0.003054542,0.001533854,0.001808675,0.00107384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007221173,"about_ca_system_score_gemma":0.001359197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00394371,"about_ca_topic_score_gemma":0.005423269,"domain_scores_codex":[0.998068,0.0004296343,0.0001195535,0.0004853065,0.0007207925,0.0001767154],"domain_scores_gemma":[0.9958977,0.001999119,0.0003850236,0.0009573074,0.0005905288,0.0001704668],"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":[0.000654714,0.0004579989,0.006358625,0.0002509479,0.0002728295,0.0004185618,0.0001857175,0.2250386,0.01693994,0.004551035,0.01745765,0.7274134],"study_design_scores_gemma":[0.00005028029,0.00009853363,0.001167441,0.000008767111,0.00002547746,0.0001164455,0.00005608439,0.9821215,0.003221507,0.01083589,0.00227983,0.00001823285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02669664,0.001049535,0.9671476,0.0003862286,0.00008806078,0.0001345761,0.0005054205,0.003355462,0.0006364111],"genre_scores_gemma":[0.4440493,0.0005337617,0.5486611,0.0003536175,0.0003011262,0.0004578608,0.003443822,0.000294214,0.00190533],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00394371,"threshold_uncertainty_score":0.01016986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1056308529088211,"score_gpt":0.3196476373088136,"score_spread":0.2140167843999925,"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."}}