{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001863645,0.0001957921,0.0001829068,0.0001166675,0.0002927425,0.0002974211,0.00261951,0.0001229315,0.00002182399],"category_scores_gemma":[0.0001322555,0.00013626,0.00003548318,0.0002859845,0.0000496266,0.004699399,0.0003098651,0.0001465811,0.00007797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000298951,"about_ca_system_score_gemma":0.0001168345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006390895,"about_ca_topic_score_gemma":0.001023407,"domain_scores_codex":[0.9983029,0.00006206945,0.0001918902,0.001045489,0.0001396306,0.0002580295],"domain_scores_gemma":[0.9959974,0.0005771026,0.00007009078,0.003176482,0.0000809767,0.00009792568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001064902,0.0004711565,0.00007300702,0.00002677107,0.00008721461,8.305026e-7,0.00007678995,0.000009124652,0.01122647,0.00004088049,0.05770346,0.9301778],"study_design_scores_gemma":[0.008352399,0.0007258672,0.003849984,0.001645862,0.00047425,0.00004242178,0.0002922225,0.1570713,0.06797116,0.0151667,0.7423624,0.002045399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009845309,0.0002938883,0.9651958,0.003746215,0.001318189,0.0002741167,0.01915984,0.000132878,0.00003376177],"genre_scores_gemma":[0.7429394,0.00363117,0.2164994,0.001007866,0.002167817,0.000192164,0.01975499,0.0001210668,0.01368622],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281324,"threshold_uncertainty_score":0.5556521,"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."}}