{"id":"W2806337402","doi":"10.1016/j.patcog.2018.05.030","title":"A fast clustering algorithm based on pruning unnecessary distance computations in DBSCAN for high-dimensional data","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":170,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"State Key Laboratory of Computer Aided Design and Computer Graphics; National Laboratory of Pattern Recognition; Fujian Provincial Department of Science and Technology; Zhejiang University; Huaqiao University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"DBSCAN; Computer science; Pruning; Computation; Cluster analysis; Noise (video); Dimension (graph theory); Algorithm; Search engine indexing; Pattern recognition (psychology); Data mining; Mathematics; Artificial intelligence; CURE data clustering algorithm; Correlation clustering; Combinatorics; Image (mathematics)","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":[0.001526959,0.001587811,0.002858595,0.00388195,0.002631173,0.0028393,0.004864905,0.001606211,0.003368411],"category_scores_gemma":[0.005181411,0.000961136,0.001441972,0.008219852,0.0010221,0.002461762,0.002253666,0.002728702,0.002483765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105563,"about_ca_system_score_gemma":0.004630564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02178555,"about_ca_topic_score_gemma":0.02654047,"domain_scores_codex":[0.9965878,0.0003973894,0.0002425756,0.0005084055,0.002023081,0.0002407754],"domain_scores_gemma":[0.9971907,0.0005422771,0.0001267934,0.0004737111,0.001545672,0.0001207541],"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":[0.0005108356,0.0002562995,0.001119197,0.0002560013,0.0002078421,0.0001278528,0.0002338914,0.06551039,0.01510171,0.01338836,0.0148116,0.8884761],"study_design_scores_gemma":[0.00006744421,0.0001477157,0.001036805,0.00003656945,0.00008391166,0.0003709462,0.0001564744,0.9480713,0.02144323,0.01499781,0.01347238,0.0001154895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005593974,0.0004367095,0.9905266,0.0001009888,0.0001627815,0.00009720369,0.0001987544,0.002254933,0.0006280711],"genre_scores_gemma":[0.02856137,0.0002821186,0.9680641,0.00008882674,0.00007140316,0.0001822055,0.0009570763,0.0002621276,0.001530829],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02178555,"threshold_uncertainty_score":0.0433175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0527162703613487,"score_gpt":0.285088083781462,"score_spread":0.2323718134201133,"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."}}