{"id":"W2755594639","doi":"10.1109/trustcom/bigdatase/icess.2017.332","title":"A Data Science and Engineering Solution for Fast K-Means Clustering of Big Data","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Scalability; Computer science; Cluster analysis; Data mining; Science and engineering; Heuristic; Task (project management); Variety (cybernetics); Centroid; Data science; Database; Artificial intelligence; Engineering","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":[0.001213429,0.0009381813,0.001013327,0.001675505,0.001737968,0.001579116,0.002551228,0.002754147,0.004297047],"category_scores_gemma":[0.005562311,0.0006937099,0.001274626,0.002898339,0.0008775573,0.002361111,0.001881612,0.001808346,0.002892403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009470125,"about_ca_system_score_gemma":0.002505592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00395345,"about_ca_topic_score_gemma":0.005228013,"domain_scores_codex":[0.9984863,0.0002274639,0.00009318033,0.0003643201,0.0007191102,0.0001096744],"domain_scores_gemma":[0.9987603,0.0002215996,0.00009991288,0.0002938673,0.0005410349,0.00008330196],"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":[0.0002764737,0.000262875,0.001329481,0.0005471038,0.0001474491,0.0003176426,0.0003263994,0.1934347,0.01409881,0.07095242,0.03114658,0.6871601],"study_design_scores_gemma":[0.00008419108,0.0001246817,0.0004232535,0.00003921257,0.00003125795,0.0005390411,0.0001617193,0.9117599,0.007050514,0.05015309,0.02958726,0.00004600312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001940948,0.0001647272,0.9952489,0.0002931552,0.0001113085,0.0000827675,0.00006964979,0.0009806826,0.001107973],"genre_scores_gemma":[0.02715077,0.0001558642,0.9703569,0.0001106573,0.00005752513,0.0001775558,0.0002749169,0.0001178641,0.001597957],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004297047,"threshold_uncertainty_score":0.01437503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.192390620466613,"score_gpt":0.3746471718461937,"score_spread":0.1822565513795807,"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."}}