{"id":"W2785593625","doi":"10.1109/ssci.2017.8285208","title":"Particle swarm optimization for large-scale clustering on apache spark","year":2017,"lang":"en","type":"article","venue":"","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"SPARK (programming language); Cluster analysis; Computer science; Particle swarm optimization; Big data; Data mining; Canopy clustering algorithm; CURE data clustering algorithm; Correlation clustering; Algorithm; Machine learning","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":[0.001065122,0.0007792792,0.0008939293,0.0004930226,0.001016558,0.0008494103,0.001501819,0.0007732051,0.002903151],"category_scores_gemma":[0.002402563,0.000437583,0.0007892302,0.0008564779,0.0004871991,0.0006276811,0.0010097,0.001098078,0.0009552326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008297339,"about_ca_system_score_gemma":0.001945675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0113542,"about_ca_topic_score_gemma":0.008574797,"domain_scores_codex":[0.999432,0.0001491089,0.00003404939,0.0000786929,0.0002371543,0.00006882824],"domain_scores_gemma":[0.9992373,0.0002871655,0.00005341659,0.00009939489,0.000253079,0.00006960913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000957814,0.00007597845,0.0006092288,0.00009192489,0.00005674627,0.0001073249,0.00009467436,0.9379448,0.002416208,0.0157359,0.00701882,0.0357526],"study_design_scores_gemma":[0.00002091055,0.000008583652,0.00007339554,0.000002239593,0.000002713705,0.000009761464,0.00001274475,0.9938471,0.000670854,0.003502181,0.001844203,0.000005373991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01160774,0.0001083229,0.978227,0.0002058366,0.00008496,0.00009453815,0.0001522277,0.003581078,0.005938397],"genre_scores_gemma":[0.2207623,0.0001379889,0.7731828,0.00009782709,0.00003785498,0.0004073463,0.0006249088,0.0008512641,0.003897764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0113542,"threshold_uncertainty_score":0.02257621,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05665801471600643,"score_gpt":0.3355027272439812,"score_spread":0.2788447125279747,"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."}}