{"id":"W3184658021","doi":"10.1109/ficloud49777.2021.00042","title":"A Parallel Processing Technique for Extracting and Storing User Specified Data","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Raw data; SPARK (programming language); Latency (audio); Data processing; Data set; Set (abstract data type); Data mining; Filter (signal processing); Bloom filter; Big data; Process (computing); Volume (thermodynamics); Database; Artificial intelligence; Operating system; Algorithm","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":[0.001116545,0.001447449,0.001031869,0.00207849,0.001125648,0.001751295,0.002030453,0.0005141235,0.003503167],"category_scores_gemma":[0.004163662,0.0007153234,0.001076554,0.005395821,0.0006887085,0.002446905,0.001159341,0.001578172,0.002865958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006616328,"about_ca_system_score_gemma":0.002363573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003150594,"about_ca_topic_score_gemma":0.003410444,"domain_scores_codex":[0.9983571,0.0001637073,0.0002202301,0.0004248418,0.0007047821,0.000129292],"domain_scores_gemma":[0.9975924,0.0004978571,0.000238956,0.0008885517,0.0007039148,0.00007829758],"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":[0.001555508,0.0004842405,0.004714151,0.0008959852,0.0003591868,0.0009752962,0.0005748872,0.01682118,0.1036135,0.01515731,0.04800619,0.8068426],"study_design_scores_gemma":[0.0004846068,0.001043402,0.005767733,0.0001814821,0.0003657268,0.004099983,0.0004782571,0.470766,0.2974083,0.0520339,0.1670289,0.0003415682],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009660644,0.0004473548,0.9705331,0.000297267,0.0002349493,0.0004201137,0.001063794,0.01470602,0.00263669],"genre_scores_gemma":[0.1229615,0.0007772454,0.8663812,0.0003344665,0.0001845118,0.0007883466,0.002755841,0.0006282685,0.005188616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003503167,"threshold_uncertainty_score":0.01171929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1144929990057161,"score_gpt":0.3446471840065037,"score_spread":0.2301541850007875,"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."}}