{"id":"W1983150145","doi":"10.1109/icdm.2014.63","title":"Towards Scalable and Accurate Online Feature Selection for Big Data","year":2014,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Feature selection; Computer science; Scalability; Big data; Benchmark (surveying); Curse of dimensionality; Feature (linguistics); Data mining; Dimensionality reduction; Selection (genetic algorithm); Artificial intelligence; Machine learning; Feature extraction; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001662138,0.00005818834,0.00006571757,0.00003489445,0.00008896654,0.0001263798,0.0003048012,0.00004910583,0.000005787581],"category_scores_gemma":[0.0000625445,0.00004284193,0.00001008595,0.0001190045,0.000008069172,0.0004748336,0.000209087,0.00004972525,0.000009811792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004075466,"about_ca_system_score_gemma":0.00001990185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002957179,"about_ca_topic_score_gemma":0.00008570666,"domain_scores_codex":[0.9994638,0.00001799713,0.00006063529,0.0002679708,0.00007363936,0.0001159902],"domain_scores_gemma":[0.9995543,0.0000386404,0.0000255976,0.0002773189,0.00005819152,0.00004598002],"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":[0.000008921164,0.00003911516,0.0001021737,0.00002226872,0.000005822634,8.512288e-8,0.00003035665,0.00001498742,0.003922509,0.0009605947,0.167165,0.8277282],"study_design_scores_gemma":[0.0003842689,0.00008578158,0.0008100712,0.00001919543,0.000005164758,0.000007096301,0.00001214635,0.7551439,0.008103752,0.002458501,0.2328564,0.0001136584],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01265133,0.00002962957,0.9809325,0.004762238,0.0004130662,0.0001210234,0.00002096966,0.0001240048,0.0009451842],"genre_scores_gemma":[0.3069004,0.0001217408,0.6782386,0.004161144,0.001176157,0.00002873188,0.0004805081,0.00001758608,0.008875118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8276145,"threshold_uncertainty_score":0.1747043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06871331023400729,"score_gpt":0.2985533757496955,"score_spread":0.2298400655156882,"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."}}