{"id":"W4391175008","doi":"10.56367/oag-041-10846","title":"Reducing data volume in big data: Parallel processing based data filtering techniques","year":2024,"lang":"en","type":"article","venue":"Open Access Government","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Volume (thermodynamics); Big data; Computer science; Data processing; Data mining; 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":[0.003045633,0.001392525,0.001960946,0.003713962,0.00162434,0.003396846,0.002178307,0.001383921,0.002951319],"category_scores_gemma":[0.01005338,0.0008275415,0.002289136,0.007502542,0.001403692,0.005260755,0.001803344,0.002559645,0.001813261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001277567,"about_ca_system_score_gemma":0.002064299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004441149,"about_ca_topic_score_gemma":0.003116744,"domain_scores_codex":[0.9969292,0.0005231416,0.0002326464,0.000491305,0.001600976,0.0002227091],"domain_scores_gemma":[0.9929375,0.003007907,0.0006299061,0.001393602,0.001867703,0.0001632917],"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":[0.0004247475,0.0004741619,0.004711381,0.0006876878,0.0004305932,0.0003209809,0.0004882218,0.06658731,0.01519572,0.04760333,0.03380911,0.8292668],"study_design_scores_gemma":[0.0001597243,0.0003570387,0.004192385,0.0002158582,0.0002747214,0.00085866,0.0004479216,0.6773463,0.02752423,0.2137618,0.07472032,0.0001410521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006419741,0.003397201,0.9814892,0.002825115,0.0004701031,0.0001980051,0.0002140917,0.001520284,0.003466194],"genre_scores_gemma":[0.1464052,0.007199572,0.8343651,0.001409564,0.001499729,0.0004879633,0.001264352,0.0005159712,0.006852449],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004441149,"threshold_uncertainty_score":0.01610702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6516426195564557,"score_gpt":0.5994076944851713,"score_spread":0.05223492507128447,"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."}}