{"id":"W3011249019","doi":"10.1109/access.2020.2980942","title":"Analysis of Dimensionality Reduction Techniques on Big Data","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":869,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Dimensionality reduction; Machine learning; Artificial intelligence; Computer science; Random forest; Naive Bayes classifier; Principal component analysis; Linear discriminant analysis; Decision tree; Support vector machine; Data mining","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":[0.0001403159,0.00006590081,0.0001439044,0.0001385231,0.00006914612,0.00005872281,0.001552158,0.00003854608,0.000009522806],"category_scores_gemma":[0.00001565145,0.00005985444,0.00005613867,0.001814123,0.00003121055,0.0003850672,0.0003502964,0.00007385146,0.000004598381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001200241,"about_ca_system_score_gemma":0.00002168308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000094598,"about_ca_topic_score_gemma":0.000003583853,"domain_scores_codex":[0.9991386,0.00002849342,0.0001968401,0.0003860218,0.000177263,0.0000728017],"domain_scores_gemma":[0.9987114,0.00002523493,0.000132714,0.001005406,0.00007478876,0.0000504692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003627552,0.0003714933,0.001811558,0.00003764938,0.0005144005,0.00000320375,0.000196865,0.0006753759,0.07902527,0.03651275,0.02504219,0.855773],"study_design_scores_gemma":[0.00007177637,0.0001354222,0.007781823,0.00001209482,0.0001914358,0.000002068989,0.000009878144,0.08848158,0.8816137,0.002758411,0.01869504,0.0002468081],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02320545,0.000009847308,0.9730942,0.00230666,0.000079081,0.000127322,0.00002878555,0.0003430776,0.0008055795],"genre_scores_gemma":[0.9906361,0.00001782991,0.008779062,0.0004127462,0.00009753861,0.00001916857,0.00001802825,0.000003515261,0.00001600741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9674307,"threshold_uncertainty_score":0.2884322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1846125289162926,"score_gpt":0.3704329397476505,"score_spread":0.1858204108313579,"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."}}