{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003565673,0.00013486,0.0001220751,0.00019661,0.000158266,0.0001989416,0.000703599,0.00003141949,0.00002071235],"category_scores_gemma":[0.00002504603,0.0001412653,0.00002046307,0.00029478,0.00003574783,0.000940343,0.0003676299,0.00008518115,0.0000651057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004135518,"about_ca_system_score_gemma":0.00002293476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009584895,"about_ca_topic_score_gemma":0.0002939348,"domain_scores_codex":[0.9986662,0.00005386156,0.0002299299,0.0005719177,0.0002272155,0.0002508695],"domain_scores_gemma":[0.9990994,0.0001415437,0.0001022934,0.0005301538,0.0000798124,0.00004681476],"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":[0.000008688505,0.00009568091,0.0001961983,0.00002768021,0.000006878696,0.000007424597,0.00005127994,0.0005045374,0.000008911801,0.00002897568,0.0007217252,0.998342],"study_design_scores_gemma":[0.0008582362,0.000125416,0.002813788,0.000224276,0.000007137425,0.00000137838,0.00001487956,0.9942054,0.0001003468,0.001132352,0.0003241886,0.0001925826],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00311879,0.000004673942,0.9943472,0.0007311655,0.0005553772,0.0003389852,0.0006363722,0.0001027165,0.0001647717],"genre_scores_gemma":[0.5817257,0.00000203262,0.4111517,0.001401996,0.0003542075,0.00007778685,0.005231484,0.0000205035,0.00003458771],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9981495,"threshold_uncertainty_score":0.5760633,"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."}}