{"id":"W2794499723","doi":"10.1109/hpccws.2017.00013","title":"A Survey and Recommendations for Distributed, Parallel, Single Pass, Incremental Bayesian Classification Based on MapReduce for Big Data","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Big data; Computer science; Scalability; Cloud computing; Analytics; Bayesian probability; Variety (cybernetics); Volume (thermodynamics); Data science; Process (computing); Data mining; Predictive analytics; Distributed computing; Machine learning; Artificial intelligence; 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":[0.003342489,0.001159114,0.001525058,0.002672942,0.0009784348,0.002764037,0.005143948,0.001577318,0.005397748],"category_scores_gemma":[0.01097606,0.0009771721,0.001714926,0.00722333,0.0007314344,0.006971255,0.001570736,0.002902186,0.003603862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001559675,"about_ca_system_score_gemma":0.003083214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009040779,"about_ca_topic_score_gemma":0.00782946,"domain_scores_codex":[0.9970783,0.000529603,0.0002644249,0.0005657924,0.001328255,0.0002336329],"domain_scores_gemma":[0.9948257,0.002121514,0.0002093326,0.0008790686,0.001670389,0.0002940543],"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":[0.0002265886,0.0004418297,0.003633586,0.003686962,0.0001766572,0.0001437662,0.0001960239,0.01600058,0.002686719,0.03270817,0.1272626,0.8128365],"study_design_scores_gemma":[0.0001090469,0.0002915458,0.004348293,0.001890347,0.0002208947,0.0009485966,0.0007270743,0.2073898,0.006659089,0.08942773,0.6878392,0.0001483974],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.007272445,0.2476241,0.6940813,0.01813855,0.003469056,0.0005802754,0.001068407,0.00782265,0.01994311],"genre_scores_gemma":[0.091844,0.3179979,0.5597782,0.007809842,0.003923152,0.0006900992,0.005563687,0.001442731,0.01095038],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009040779,"threshold_uncertainty_score":0.01805723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2549859210001608,"score_gpt":0.3650382667381168,"score_spread":0.110052345737956,"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."}}