{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00144097,0.00008841442,0.0001219861,0.0001287427,0.0004708431,0.000459219,0.008214709,0.00002386034,4.744439e-7],"category_scores_gemma":[0.001348787,0.00008319418,0.000007418833,0.0001560074,0.0002667851,0.003743516,0.01696884,0.00007600075,0.000001075829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003645338,"about_ca_system_score_gemma":0.0001513935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008996149,"about_ca_topic_score_gemma":0.00008417168,"domain_scores_codex":[0.9983594,0.000005726879,0.000157113,0.0006992225,0.0004208098,0.0003577597],"domain_scores_gemma":[0.994667,0.00008882165,0.00008609359,0.004874242,0.0001829537,0.0001008717],"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":[0.000007094402,0.00002209238,0.00005914275,0.0001444598,0.00001103985,0.000002976371,0.0001304874,0.00111313,0.0335121,0.00186404,0.0001312533,0.9630022],"study_design_scores_gemma":[0.0002282959,0.00003256884,0.0009100693,0.00003509601,0.000001876568,0.00001189667,0.000009732321,0.9954348,0.000933462,0.00005516647,0.002250067,0.00009693076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003967523,0.00003091391,0.9981433,0.0004846639,0.0003326189,0.0001849902,0.00008464579,0.00005717278,0.0002849881],"genre_scores_gemma":[0.176021,0.00002349058,0.8237185,0.00001175742,0.0001022301,0.000006808843,0.000009848374,0.000009218367,0.00009716055],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9943217,"threshold_uncertainty_score":0.9971513,"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."}}