{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007154464,0.0001113522,0.0001374522,0.00005646711,0.0006852621,0.0008226198,0.001128332,0.00005089742,0.0001484361],"category_scores_gemma":[0.0005266016,0.00009818281,0.00005403955,0.00009996638,0.00003077599,0.0005573224,0.0003959338,0.00007977372,0.00009023414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003542179,"about_ca_system_score_gemma":0.00004130805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009600481,"about_ca_topic_score_gemma":0.00001357425,"domain_scores_codex":[0.9986179,0.00004659309,0.0002035217,0.0003986721,0.0003401989,0.0003931004],"domain_scores_gemma":[0.9982601,0.0001251506,0.0001098989,0.001168373,0.0001844627,0.0001519819],"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":[0.00004678163,0.0003262562,0.0005140523,0.00004378903,0.00003085045,0.000006648058,0.0004913157,0.9083567,0.00007971368,0.05071148,0.003256322,0.03613612],"study_design_scores_gemma":[0.0007139072,0.00008215578,0.0002535713,0.000008186168,0.000002993682,0.000001561603,0.00001688625,0.9936182,0.002965776,0.0002376318,0.001974397,0.0001247498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003577051,0.000008190013,0.9878991,0.00255008,0.000333905,0.0003820061,0.000004745342,0.0001366211,0.008327607],"genre_scores_gemma":[0.1206756,0.00001448915,0.8738837,0.0003336591,0.0001109308,0.00007471931,0.000005129074,0.00001726939,0.004884529],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1203179,"threshold_uncertainty_score":0.7932541,"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."}}